├── .gitignore ├── LICENSE ├── README.md ├── analyze ├── analyze_for_vim.py ├── attnmap.py ├── clseval.py ├── convnexts4nd │ ├── __init__.py │ ├── convnext_timm.py │ ├── extensions │ │ └── kernels │ │ │ ├── README.md │ │ │ ├── benchmark_cauchy.py │ │ │ ├── benchmark_cauchy_tune.py │ │ │ ├── cauchy.cpp │ │ │ ├── cauchy.py │ │ │ ├── cauchy_cuda.cu │ │ │ ├── map.h │ │ │ ├── setup.py │ │ │ ├── test_cauchy.py │ │ │ ├── test_vandermonde.py │ │ │ ├── tune_cauchy.py │ │ │ ├── tune_cauchy.sh │ │ │ ├── tuner.py │ │ │ ├── tuning_setup.py │ │ │ └── vandermonde.py │ ├── readme.md │ ├── src │ │ ├── callbacks │ │ │ ├── norms.py │ │ │ ├── params.py │ │ │ ├── progressive_resizing.py │ │ │ ├── timer.py │ │ │ └── wandb.py │ │ ├── dataloaders │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── audio.py │ │ │ ├── base.py │ │ │ ├── basic.py │ │ │ ├── datasets │ │ │ │ ├── adding.py │ │ │ │ ├── celeba.py │ │ │ │ ├── copying.py │ │ │ │ ├── delay.py │ │ │ │ ├── music.py │ │ │ │ ├── reconstruct.py │ │ │ │ └── sc.py │ │ │ ├── et.py │ │ │ ├── lm.py │ │ │ ├── lra.py │ │ │ ├── prepare │ │ │ │ └── bidmc │ │ │ │ │ ├── README.md │ │ │ │ │ ├── data.ipynb │ │ │ │ │ ├── data_loader.py │ │ │ │ │ └── process_data.py │ │ │ ├── synthetic.py │ │ │ ├── ts.py │ │ │ ├── utils │ │ │ │ ├── cifar_augmentations.py │ │ │ │ ├── signal.py │ │ │ │ ├── timm_mixup.py │ │ │ │ ├── video_loader.py │ │ │ │ └── vocabulary.py │ │ │ └── vision.py │ │ ├── models │ │ │ ├── README.md │ │ │ ├── baselines │ │ │ │ ├── ckconv.py │ │ │ │ ├── convnext_timm.py │ │ │ │ ├── gru.py │ │ │ │ ├── lipschitzrnn.py │ │ │ │ ├── lstm.py │ │ │ │ ├── nonaka │ │ │ │ │ ├── LICENSE │ │ │ │ │ ├── README.md │ │ │ │ │ ├── basic_conv1d.py │ │ │ │ │ ├── inception.py │ │ │ │ │ ├── resnet.py │ │ │ │ │ └── xresnet.py │ │ │ │ ├── nrde.py │ │ │ │ ├── odelstm.py │ │ │ │ ├── resnet.py │ │ │ │ ├── resnet_timm.py │ │ │ │ ├── samplernn.py │ │ │ │ ├── transformer.py │ │ │ │ ├── unicornn.py │ │ │ │ ├── vit.py │ │ │ │ ├── vit_all.py │ │ │ │ └── wavenet.py │ │ │ ├── functional │ │ │ │ ├── cauchy.py │ │ │ │ ├── krylov.py │ │ │ │ ├── toeplitz.py │ │ │ │ ├── unroll.py │ │ │ │ └── vandermonde.py │ │ │ ├── hippo │ │ │ │ ├── hippo.py │ │ │ │ ├── transition.py │ │ │ │ └── visualizations.py │ │ │ ├── nn │ │ │ │ ├── __init__.py │ │ │ │ ├── activation.py │ │ │ │ ├── adaptive_softmax.py │ │ │ │ ├── dropout.py │ │ │ │ ├── dxt.py │ │ │ │ ├── exprnn │ │ │ │ │ ├── README.md │ │ │ │ │ ├── expm32.py │ │ │ │ │ ├── initialization.py │ │ │ │ │ ├── orthogonal.py │ │ │ │ │ ├── parametrization.py │ │ │ │ │ └── trivializations.py │ │ │ │ ├── gate.py │ │ │ │ ├── initialization.py │ │ │ │ ├── linear.py │ │ │ │ ├── normalization.py │ │ │ │ ├── orthogonal.py │ │ │ │ ├── residual.py │ │ │ │ └── utils.py │ │ │ ├── s4 │ │ │ │ └── README.md │ │ │ └── sequence │ │ │ │ ├── README.md │ │ │ │ ├── __init__.py │ │ │ │ ├── attention │ │ │ │ ├── linear.py │ │ │ │ ├── mha.py │ │ │ │ └── performer.py │ │ │ │ ├── backbones │ │ │ │ ├── block.py │ │ │ │ ├── model.py │ │ │ │ ├── sashimi.py │ │ │ │ └── unet.py │ │ │ │ ├── base.py │ │ │ │ ├── convs │ │ │ │ ├── conv1d.py │ │ │ │ └── conv2d.py │ │ │ │ ├── kernels │ │ │ │ ├── __init__.py │ │ │ │ ├── dplr.py │ │ │ │ ├── fftconv.py │ │ │ │ ├── kernel.py │ │ │ │ └── ssm.py │ │ │ │ ├── modules │ │ │ │ ├── ffn.py │ │ │ │ ├── lssl.py │ │ │ │ ├── megablock.py │ │ │ │ ├── pool.py │ │ │ │ ├── s4block.py │ │ │ │ └── s4nd.py │ │ │ │ └── rnns │ │ │ │ ├── __init__.py │ │ │ │ ├── cells │ │ │ │ ├── __init__.py │ │ │ │ ├── basic.py │ │ │ │ ├── hippo.py │ │ │ │ ├── memory.py │ │ │ │ ├── minimalrnn.py │ │ │ │ └── timestamp.py │ │ │ │ ├── qrnn.py │ │ │ │ ├── rnn.py │ │ │ │ └── sru.py │ │ ├── tasks │ │ │ ├── decoders.py │ │ │ ├── encoders.py │ │ │ ├── metrics.py │ │ │ └── tasks.py │ │ └── utils │ │ │ ├── __init__.py │ │ │ ├── config.py │ │ │ ├── distributed.py │ │ │ ├── optim │ │ │ ├── ema.py │ │ │ ├── lamb.py │ │ │ └── schedulers.py │ │ │ ├── optim_groups.py │ │ │ ├── permutations.py │ │ │ ├── registry.py │ │ │ └── train.py │ └── vit_all.py ├── erf.py ├── eval.py ├── flops.py ├── loss.py ├── mmpretrain_configs │ ├── configs │ │ ├── _base_ │ │ │ ├── datasets │ │ │ │ ├── cifar100_bs16.py │ │ │ │ ├── cifar10_bs16.py │ │ │ │ ├── coco_caption.py │ │ │ │ ├── coco_okvqa.py │ │ │ │ ├── coco_retrieval.py │ │ │ │ ├── coco_vg_vqa.py │ │ │ │ ├── coco_vqa.py │ │ │ │ ├── cub_bs8_384.py │ │ │ │ ├── cub_bs8_448.py │ │ │ │ ├── flickr30k_caption.py │ │ │ │ ├── flickr30k_retrieval.py │ │ │ │ ├── gqa.py │ │ │ │ ├── imagenet21k_bs128.py │ │ │ │ ├── imagenet_bs128_mbv3.py │ │ │ │ ├── imagenet_bs128_poolformer_medium_224.py │ │ │ │ ├── imagenet_bs128_poolformer_small_224.py │ │ │ │ ├── imagenet_bs128_revvit_224.py │ │ │ │ ├── imagenet_bs128_riformer_medium_384.py │ │ │ │ ├── imagenet_bs128_riformer_small_384.py │ │ │ │ ├── imagenet_bs128_vig_224.py │ │ │ │ ├── imagenet_bs16_eva_196.py │ │ │ │ ├── imagenet_bs16_eva_336.py │ │ │ │ ├── imagenet_bs16_eva_448.py │ │ │ │ ├── imagenet_bs16_eva_560.py │ │ │ │ ├── imagenet_bs16_pil_bicubic_384.py │ │ │ │ ├── imagenet_bs256_beitv2.py │ │ │ │ ├── imagenet_bs256_davit_224.py │ │ │ │ ├── imagenet_bs256_itpn.py │ │ │ │ ├── imagenet_bs256_levit_224.py │ │ │ │ ├── imagenet_bs256_rsb_a12.py │ │ │ │ ├── imagenet_bs256_rsb_a3.py │ │ │ │ ├── imagenet_bs256_simmim_192.py │ │ │ │ ├── imagenet_bs256_swin_192.py │ │ │ │ ├── imagenet_bs32.py │ │ │ │ ├── imagenet_bs32_byol.py │ │ │ │ ├── imagenet_bs32_mocov2.py │ │ │ │ ├── imagenet_bs32_pil_bicubic.py │ │ │ │ ├── imagenet_bs32_pil_resize.py │ │ │ │ ├── imagenet_bs32_simclr.py │ │ │ │ ├── imagenet_bs512_mae.py │ │ │ │ ├── imagenet_bs512_mocov3.py │ │ │ │ ├── imagenet_bs64.py │ │ │ │ ├── imagenet_bs64_autoaug.py │ │ │ │ ├── imagenet_bs64_clip_224.py │ │ │ │ ├── imagenet_bs64_clip_384.py │ │ │ │ ├── imagenet_bs64_clip_448.py │ │ │ │ ├── imagenet_bs64_convmixer_224.py │ │ │ │ ├── imagenet_bs64_deit3_224.py │ │ │ │ ├── imagenet_bs64_deit3_384.py │ │ │ │ ├── imagenet_bs64_edgenext_256.py │ │ │ │ ├── imagenet_bs64_hivit_224.py │ │ │ │ ├── imagenet_bs64_mixer_224.py │ │ │ │ ├── imagenet_bs64_pil_resize.py │ │ │ │ ├── imagenet_bs64_pil_resize_autoaug.py │ │ │ │ ├── imagenet_bs64_swin_224.py │ │ │ │ ├── imagenet_bs64_swin_256.py │ │ │ │ ├── imagenet_bs64_swin_384.py │ │ │ │ ├── imagenet_bs64_t2t_224.py │ │ │ │ ├── imagenet_bs8_pil_bicubic_320.py │ │ │ │ ├── inshop_bs32_448.py │ │ │ │ ├── nlvr2.py │ │ │ │ ├── nocaps.py │ │ │ │ ├── ocrvqa.py │ │ │ │ ├── pipelines │ │ │ │ │ ├── auto_aug.py │ │ │ │ │ └── rand_aug.py │ │ │ │ ├── refcoco.py │ │ │ │ ├── vizwiz.py │ │ │ │ ├── voc_bs16.py │ │ │ │ └── vsr.py │ │ │ ├── default_runtime.py │ │ │ ├── models │ │ │ │ ├── conformer │ │ │ │ │ ├── base-p16.py │ │ │ │ │ ├── small-p16.py │ │ │ │ │ ├── small-p32.py │ │ │ │ │ └── tiny-p16.py │ │ │ │ ├── convmixer │ │ │ │ │ ├── convmixer-1024-20.py │ │ │ │ │ ├── convmixer-1536-20.py │ │ │ │ │ └── convmixer-768-32.py │ │ │ │ ├── convnext │ │ │ │ │ ├── __pycache__ │ │ │ │ │ │ └── convnext-tiny.cpython-310.pyc │ │ │ │ │ ├── convnext-base.py │ │ │ │ │ ├── convnext-large.py │ │ │ │ │ ├── convnext-small.py │ │ │ │ │ ├── convnext-tiny.py │ │ │ │ │ └── convnext-xlarge.py │ │ │ │ ├── convnext_v2 │ │ │ │ │ ├── atto.py │ │ │ │ │ ├── base.py │ │ │ │ │ ├── femto.py │ │ │ │ │ ├── huge.py │ │ │ │ │ ├── large.py │ │ │ │ │ ├── nano.py │ │ │ │ │ ├── pico.py │ │ │ │ │ └── tiny.py │ │ │ │ ├── davit │ │ │ │ │ ├── davit-base.py │ │ │ │ │ ├── davit-small.py │ │ │ │ │ └── davit-tiny.py │ │ │ │ ├── deit3 │ │ │ │ │ ├── deit3-base-p16-224.py │ │ │ │ │ ├── deit3-base-p16-384.py │ │ │ │ │ ├── deit3-huge-p14-224.py │ │ │ │ │ ├── deit3-large-p16-224.py │ │ │ │ │ ├── deit3-large-p16-384.py │ │ │ │ │ ├── deit3-medium-p16-224.py │ │ │ │ │ ├── deit3-small-p16-224.py │ │ │ │ │ └── deit3-small-p16-384.py │ │ │ │ ├── densenet │ │ │ │ │ ├── densenet121.py │ │ │ │ │ ├── densenet161.py │ │ │ │ │ ├── densenet169.py │ │ │ │ │ └── densenet201.py │ │ │ │ ├── edgenext │ │ │ │ │ ├── edgenext-base.py │ │ │ │ │ ├── edgenext-small.py │ │ │ │ │ ├── edgenext-xsmall.py │ │ │ │ │ └── edgenext-xxsmall.py │ │ │ │ ├── efficientformer-l1.py │ │ │ │ ├── efficientnet_b0.py │ │ │ │ ├── efficientnet_b1.py │ │ │ │ ├── efficientnet_b2.py │ │ │ │ ├── efficientnet_b3.py │ │ │ │ ├── efficientnet_b4.py │ │ │ │ ├── efficientnet_b5.py │ │ │ │ ├── efficientnet_b6.py │ │ │ │ ├── efficientnet_b7.py │ │ │ │ ├── efficientnet_b8.py │ │ │ │ ├── efficientnet_em.py │ │ │ │ ├── efficientnet_es.py │ │ │ │ ├── efficientnet_l2.py │ │ │ │ ├── efficientnet_v2 │ │ │ │ │ ├── efficientnetv2_b0.py │ │ │ │ │ ├── efficientnetv2_b1.py │ │ │ │ │ ├── efficientnetv2_b2.py │ │ │ │ │ ├── efficientnetv2_b3.py │ │ │ │ │ ├── efficientnetv2_l.py │ │ │ │ │ ├── efficientnetv2_m.py │ │ │ │ │ ├── efficientnetv2_s.py │ │ │ │ │ └── efficientnetv2_xl.py │ │ │ │ ├── eva │ │ │ │ │ ├── eva-g.py │ │ │ │ │ └── eva-l.py │ │ │ │ ├── hivit │ │ │ │ │ ├── base_224.py │ │ │ │ │ ├── small_224.py │ │ │ │ │ └── tiny_224.py │ │ │ │ ├── hornet │ │ │ │ │ ├── hornet-base-gf.py │ │ │ │ │ ├── hornet-base.py │ │ │ │ │ ├── hornet-large-gf.py │ │ │ │ │ ├── hornet-large-gf384.py │ │ │ │ │ ├── hornet-large.py │ │ │ │ │ ├── hornet-small-gf.py │ │ │ │ │ ├── hornet-small.py │ │ │ │ │ ├── hornet-tiny-gf.py │ │ │ │ │ └── hornet-tiny.py │ │ │ │ ├── hrnet │ │ │ │ │ ├── hrnet-w18.py │ │ │ │ │ ├── hrnet-w30.py │ │ │ │ │ ├── hrnet-w32.py │ │ │ │ │ ├── hrnet-w40.py │ │ │ │ │ ├── hrnet-w44.py │ │ │ │ │ ├── hrnet-w48.py │ │ │ │ │ └── hrnet-w64.py │ │ │ │ ├── inception_v3.py │ │ │ │ ├── itpn_hivit-base-p16.py │ │ │ │ ├── levit-256-p16.py │ │ │ │ ├── mae_hivit-base-p16.py │ │ │ │ ├── mae_vit-base-p16.py │ │ │ │ ├── mixmim │ │ │ │ │ └── mixmim_base.py │ │ │ │ ├── mlp_mixer_base_patch16.py │ │ │ │ ├── mlp_mixer_large_patch16.py │ │ │ │ ├── mobilenet_v2_1x.py │ │ │ │ ├── mobilenet_v3 │ │ │ │ │ ├── mobilenet_v3_large_imagenet.py │ │ │ │ │ ├── mobilenet_v3_small_050_imagenet.py │ │ │ │ │ ├── mobilenet_v3_small_075_imagenet.py │ │ │ │ │ ├── mobilenet_v3_small_cifar.py │ │ │ │ │ └── mobilenet_v3_small_imagenet.py │ │ │ │ ├── mobileone │ │ │ │ │ ├── mobileone_s0.py │ │ │ │ │ ├── mobileone_s1.py │ │ │ │ │ ├── mobileone_s2.py │ │ │ │ │ ├── mobileone_s3.py │ │ │ │ │ └── mobileone_s4.py │ │ │ │ ├── mobilevit │ │ │ │ │ ├── mobilevit_s.py │ │ │ │ │ ├── mobilevit_xs.py │ │ │ │ │ └── mobilevit_xxs.py │ │ │ │ ├── mvit │ │ │ │ │ ├── mvitv2-base.py │ │ │ │ │ ├── mvitv2-large.py │ │ │ │ │ ├── mvitv2-small.py │ │ │ │ │ └── mvitv2-tiny.py │ │ │ │ ├── poolformer │ │ │ │ │ ├── poolformer_m36.py │ │ │ │ │ ├── poolformer_m48.py │ │ │ │ │ ├── poolformer_s12.py │ │ │ │ │ ├── poolformer_s24.py │ │ │ │ │ └── poolformer_s36.py │ │ │ │ ├── regnet │ │ │ │ │ ├── regnetx_1.6gf.py │ │ │ │ │ ├── regnetx_12gf.py │ │ │ │ │ ├── regnetx_3.2gf.py │ │ │ │ │ ├── regnetx_4.0gf.py │ │ │ │ │ ├── regnetx_400mf.py │ │ │ │ │ ├── regnetx_6.4gf.py │ │ │ │ │ ├── regnetx_8.0gf.py │ │ │ │ │ └── regnetx_800mf.py │ │ │ │ ├── replknet-31B_in1k.py │ │ │ │ ├── replknet-31L_in1k.py │ │ │ │ ├── replknet-XL_in1k.py │ │ │ │ ├── repmlp-base_224.py │ │ │ │ ├── repvgg-A0_in1k.py │ │ │ │ ├── repvgg-B3_lbs-mixup_in1k.py │ │ │ │ ├── res2net101-w26-s4.py │ │ │ │ ├── res2net50-w14-s8.py │ │ │ │ ├── res2net50-w26-s4.py │ │ │ │ ├── res2net50-w26-s6.py │ │ │ │ ├── res2net50-w26-s8.py │ │ │ │ ├── res2net50-w48-s2.py │ │ │ │ ├── resnest101.py │ │ │ │ ├── resnest200.py │ │ │ │ ├── resnest269.py │ │ │ │ ├── resnest50.py │ │ │ │ ├── resnet101.py │ │ │ │ ├── resnet101_cifar.py │ │ │ │ ├── resnet152.py │ │ │ │ ├── resnet152_cifar.py │ │ │ │ ├── resnet18.py │ │ │ │ ├── resnet18_cifar.py │ │ │ │ ├── resnet34.py │ │ │ │ ├── resnet34_cifar.py │ │ │ │ ├── resnet34_gem.py │ │ │ │ ├── resnet50.py │ │ │ │ ├── resnet50_cifar.py │ │ │ │ ├── resnet50_cifar_cutmix.py │ │ │ │ ├── resnet50_cifar_mixup.py │ │ │ │ ├── resnet50_cutmix.py │ │ │ │ ├── resnet50_label_smooth.py │ │ │ │ ├── resnet50_mixup.py │ │ │ │ ├── resnetv1c50.py │ │ │ │ ├── resnetv1d101.py │ │ │ │ ├── resnetv1d152.py │ │ │ │ ├── resnetv1d50.py │ │ │ │ ├── resnext101_32x4d.py │ │ │ │ ├── resnext101_32x8d.py │ │ │ │ ├── resnext152_32x4d.py │ │ │ │ ├── resnext50_32x4d.py │ │ │ │ ├── revvit │ │ │ │ │ ├── revvit-base.py │ │ │ │ │ └── revvit-small.py │ │ │ │ ├── seresnet101.py │ │ │ │ ├── seresnet50.py │ │ │ │ ├── seresnext101_32x4d.py │ │ │ │ ├── seresnext50_32x4d.py │ │ │ │ ├── shufflenet_v1_1x.py │ │ │ │ ├── shufflenet_v2_1x.py │ │ │ │ ├── swin_transformer │ │ │ │ │ ├── __pycache__ │ │ │ │ │ │ └── tiny_224.cpython-310.pyc │ │ │ │ │ ├── base_224.py │ │ │ │ │ ├── base_384.py │ │ │ │ │ ├── large_224.py │ │ │ │ │ ├── large_384.py │ │ │ │ │ ├── small_224.py │ │ │ │ │ └── tiny_224.py │ │ │ │ ├── swin_transformer_v2 │ │ │ │ │ ├── base_256.py │ │ │ │ │ ├── base_384.py │ │ │ │ │ ├── large_256.py │ │ │ │ │ ├── large_384.py │ │ │ │ │ ├── small_256.py │ │ │ │ │ └── tiny_256.py │ │ │ │ ├── t2t-vit-t-14.py │ │ │ │ ├── t2t-vit-t-19.py │ │ │ │ ├── t2t-vit-t-24.py │ │ │ │ ├── tinyvit │ │ │ │ │ ├── tinyvit-11m.py │ │ │ │ │ ├── tinyvit-21m.py │ │ │ │ │ └── tinyvit-5m.py │ │ │ │ ├── tnt_s_patch16_224.py │ │ │ │ ├── twins_pcpvt_base.py │ │ │ │ ├── twins_svt_base.py │ │ │ │ ├── van │ │ │ │ │ ├── van_base.py │ │ │ │ │ ├── van_large.py │ │ │ │ │ ├── van_small.py │ │ │ │ │ └── van_tiny.py │ │ │ │ ├── vgg11.py │ │ │ │ ├── vgg11bn.py │ │ │ │ ├── vgg13.py │ │ │ │ ├── vgg13bn.py │ │ │ │ ├── vgg16.py │ │ │ │ ├── vgg16bn.py │ │ │ │ ├── vgg19.py │ │ │ │ ├── vgg19bn.py │ │ │ │ ├── vig │ │ │ │ │ ├── pyramid_vig_base.py │ │ │ │ │ ├── pyramid_vig_medium.py │ │ │ │ │ ├── pyramid_vig_small.py │ │ │ │ │ ├── pyramid_vig_tiny.py │ │ │ │ │ ├── vig_base.py │ │ │ │ │ ├── vig_small.py │ │ │ │ │ └── vig_tiny.py │ │ │ │ ├── vit-base-p16.py │ │ │ │ ├── vit-base-p32.py │ │ │ │ ├── vit-large-p16.py │ │ │ │ ├── vit-large-p32.py │ │ │ │ └── wide-resnet50.py │ │ │ └── schedules │ │ │ │ ├── cifar10_bs128.py │ │ │ │ ├── cub_bs64.py │ │ │ │ ├── imagenet_bs1024_adamw_conformer.py │ │ │ │ ├── imagenet_bs1024_adamw_hivit.py │ │ │ │ ├── imagenet_bs1024_adamw_revvit.py │ │ │ │ ├── imagenet_bs1024_adamw_swin.py │ │ │ │ ├── imagenet_bs1024_coslr.py │ │ │ │ ├── imagenet_bs1024_linearlr_bn_nowd.py │ │ │ │ ├── imagenet_bs2048.py │ │ │ │ ├── imagenet_bs2048_AdamW.py │ │ │ │ ├── imagenet_bs2048_adamw_levit.py │ │ │ │ ├── imagenet_bs2048_coslr.py │ │ │ │ ├── imagenet_bs2048_rsb.py │ │ │ │ ├── imagenet_bs256.py │ │ │ │ ├── imagenet_bs256_140e.py │ │ │ │ ├── imagenet_bs256_200e_coslr_warmup.py │ │ │ │ ├── imagenet_bs256_coslr.py │ │ │ │ ├── imagenet_bs256_coslr_coswd_300e.py │ │ │ │ ├── imagenet_bs256_epochstep.py │ │ │ │ ├── imagenet_bs4096_AdamW.py │ │ │ │ ├── imagenet_lars_coslr_200e.py │ │ │ │ ├── imagenet_lars_coslr_90e.py │ │ │ │ ├── imagenet_sgd_coslr_100e.py │ │ │ │ ├── imagenet_sgd_coslr_200e.py │ │ │ │ └── imagenet_sgd_steplr_100e.py │ │ ├── arcface │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ └── resnet50-arcface_8xb32_inshop.py │ │ ├── barlowtwins │ │ │ ├── README.md │ │ │ ├── barlowtwins_resnet50_8xb256-coslr-1000e_in1k.py │ │ │ ├── barlowtwins_resnet50_8xb256-coslr-300e_in1k.py │ │ │ ├── benchmarks │ │ │ │ └── resnet50_8xb32-linear-coslr-100e_in1k.py │ │ │ └── metafile.yml │ │ ├── beit │ │ │ ├── README.md │ │ │ ├── beit_beit-base-p16_8xb256-amp-coslr-300e_in1k.py │ │ │ ├── benchmarks │ │ │ │ ├── beit-base-p16_8xb128-coslr-100e_in1k.py │ │ │ │ └── beit-base-p16_8xb64_in1k.py │ │ │ └── metafile.yml │ │ ├── beitv2 │ │ │ ├── README.md │ │ │ ├── beitv2_beit-base-p16_8xb256-amp-coslr-1600e_in1k.py │ │ │ ├── beitv2_beit-base-p16_8xb256-amp-coslr-300e_in1k.py │ │ │ ├── benchmarks │ │ │ │ ├── beit-base-p16_8xb128-coslr-100e_in1k.py │ │ │ │ └── beit-base-p16_8xb64_in1k.py │ │ │ └── metafile.yml │ │ ├── blip │ │ │ ├── README.md │ │ │ ├── blip-base_8xb16_refcoco.py │ │ │ ├── blip-base_8xb32_caption.py │ │ │ ├── blip-base_8xb32_caption_flickr30k.py │ │ │ ├── blip-base_8xb32_nlvr.py │ │ │ ├── blip-base_8xb32_nocaps.py │ │ │ ├── blip-base_8xb32_ocrvqa.py │ │ │ ├── blip-base_8xb32_okvqa.py │ │ │ ├── blip-base_8xb32_retrieval.py │ │ │ ├── blip-base_8xb32_retrieval_flickr30k.py │ │ │ ├── blip-base_8xb32_vqa.py │ │ │ └── metafile.yml │ │ ├── blip2 │ │ │ ├── README.md │ │ │ ├── blip2-opt2.7b_8xb16_gqa.py │ │ │ ├── blip2-opt2.7b_8xb16_vqa.py │ │ │ ├── blip2-opt2.7b_8xb32_caption.py │ │ │ ├── blip2_8xb32_retrieval.py │ │ │ └── metafile.yml │ │ ├── byol │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ ├── mask-rcnn_r50-c4_ms-1x_coco.py │ │ │ │ ├── mask-rcnn_r50_fpn_ms-1x_coco.py │ │ │ │ └── resnet50_8xb512-linear-coslr-90e_in1k.py │ │ │ ├── byol_resnet50_16xb256-coslr-200e_in1k.py │ │ │ └── metafile.yml │ │ ├── cae │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ └── beit-base-p16_8xb128-coslr-100e_in1k.py │ │ │ ├── cae_beit-base-p16_8xb256-amp-coslr-300e_in1k.py │ │ │ └── metafile.yml │ │ ├── chinese_clip │ │ │ ├── README.md │ │ │ ├── cn-clip_resnet50_zeroshot-cls_cifar100.py │ │ │ ├── cn-clip_vit-base-p16_zeroshot-cls_cifar100.py │ │ │ ├── cn-clip_vit-huge-p14_zeroshot-cls_cifar100.py │ │ │ ├── cn-clip_vit-large-p14_zeroshot-cls_cifar100.py │ │ │ └── metafile.yml │ │ ├── clip │ │ │ ├── README.md │ │ │ ├── clip_vit-base-p16_zeroshot-cls_cifar100.py │ │ │ ├── clip_vit-base-p16_zeroshot-cls_in1k.py │ │ │ ├── clip_vit-large-p14_zeroshot-cls_cifar100.py │ │ │ ├── clip_vit-large-p14_zeroshot-cls_in1k.py │ │ │ ├── metafile.yml │ │ │ ├── vit-base-p16_pt-64xb64_in1k-384px.py │ │ │ ├── vit-base-p16_pt-64xb64_in1k-448px.py │ │ │ ├── vit-base-p16_pt-64xb64_in1k.py │ │ │ ├── vit-base-p32_pt-64xb64_in1k-384px.py │ │ │ ├── vit-base-p32_pt-64xb64_in1k-448px.py │ │ │ ├── vit-base-p32_pt-64xb64_in1k.py │ │ │ └── vit-large-p14_headless.py │ │ ├── conformer │ │ │ ├── README.md │ │ │ ├── conformer-base-p16_8xb128_in1k.py │ │ │ ├── conformer-small-p16_8xb128_in1k.py │ │ │ ├── conformer-small-p32_8xb128_in1k.py │ │ │ ├── conformer-tiny-p16_8xb128_in1k.py │ │ │ └── metafile.yml │ │ ├── convmixer │ │ │ ├── README.md │ │ │ ├── convmixer-1024-20_10xb64_in1k.py │ │ │ ├── convmixer-1536-20_10xb64_in1k.py │ │ │ ├── convmixer-768-32_10xb64_in1k.py │ │ │ └── metafile.yml │ │ ├── convnext │ │ │ ├── README.md │ │ │ ├── convnext-base_32xb128_in1k-384px.py │ │ │ ├── convnext-base_32xb128_in1k.py │ │ │ ├── convnext-base_32xb128_in21k.py │ │ │ ├── convnext-large_64xb64_in1k-384px.py │ │ │ ├── convnext-large_64xb64_in1k.py │ │ │ ├── convnext-large_64xb64_in21k.py │ │ │ ├── convnext-small_32xb128_in1k-384px.py │ │ │ ├── convnext-small_32xb128_in1k.py │ │ │ ├── convnext-tiny_32xb128_in1k-384px.py │ │ │ ├── convnext-tiny_32xb128_in1k.py │ │ │ ├── convnext-xlarge_64xb64_in1k-384px.py │ │ │ ├── convnext-xlarge_64xb64_in1k.py │ │ │ ├── convnext-xlarge_64xb64_in21k.py │ │ │ └── metafile.yml │ │ ├── convnext_v2 │ │ │ ├── README.md │ │ │ ├── convnext-v2-atto_32xb32_in1k.py │ │ │ ├── convnext-v2-base_32xb32_in1k-384px.py │ │ │ ├── convnext-v2-base_32xb32_in1k.py │ │ │ ├── convnext-v2-femto_32xb32_in1k.py │ │ │ ├── convnext-v2-huge_32xb32_in1k-384px.py │ │ │ ├── convnext-v2-huge_32xb32_in1k-512px.py │ │ │ ├── convnext-v2-huge_32xb32_in1k.py │ │ │ ├── convnext-v2-large_32xb32_in1k-384px.py │ │ │ ├── convnext-v2-large_32xb32_in1k.py │ │ │ ├── convnext-v2-nano_32xb32_in1k-384px.py │ │ │ ├── convnext-v2-nano_32xb32_in1k.py │ │ │ ├── convnext-v2-pico_32xb32_in1k.py │ │ │ ├── convnext-v2-tiny_32xb32_in1k-384px.py │ │ │ ├── convnext-v2-tiny_32xb32_in1k.py │ │ │ └── metafile.yml │ │ ├── cspnet │ │ │ ├── README.md │ │ │ ├── cspdarknet50_8xb32_in1k.py │ │ │ ├── cspresnet50_8xb32_in1k.py │ │ │ ├── cspresnext50_8xb32_in1k.py │ │ │ └── metafile.yml │ │ ├── csra │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ └── resnet101-csra_1xb16_voc07-448px.py │ │ ├── davit │ │ │ ├── README.md │ │ │ ├── davit-base_4xb256_in1k.py │ │ │ ├── davit-small_4xb256_in1k.py │ │ │ ├── davit-tiny_4xb256_in1k.py │ │ │ └── metafile.yml │ │ ├── deit │ │ │ ├── README.md │ │ │ ├── deit-base-distilled_16xb32_in1k-384px.py │ │ │ ├── deit-base-distilled_16xb64_in1k.py │ │ │ ├── deit-base_16xb32_in1k-384px.py │ │ │ ├── deit-base_16xb64_in1k.py │ │ │ ├── deit-small-distilled_4xb256_in1k.py │ │ │ ├── deit-small_4xb256_in1k.py │ │ │ ├── deit-tiny-distilled_4xb256_in1k.py │ │ │ ├── deit-tiny_4xb256_in1k.py │ │ │ └── metafile.yml │ │ ├── deit3 │ │ │ ├── README.md │ │ │ ├── deit3-base-p16_64xb32_in1k-384px.py │ │ │ ├── deit3-base-p16_64xb64_in1k.py │ │ │ ├── deit3-huge-p14_64xb32_in1k.py │ │ │ ├── deit3-large-p16_64xb16_in1k-384px.py │ │ │ ├── deit3-large-p16_64xb64_in1k.py │ │ │ ├── deit3-medium-p16_64xb64_in1k.py │ │ │ ├── deit3-small-p16_64xb64_in1k-384px.py │ │ │ ├── deit3-small-p16_64xb64_in1k.py │ │ │ └── metafile.yml │ │ ├── densecl │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ └── resnet50_8xb32-linear-steplr-100e_in1k.py │ │ │ ├── densecl_resnet50_8xb32-coslr-200e_in1k.py │ │ │ └── metafile.yml │ │ ├── densenet │ │ │ ├── README.md │ │ │ ├── densenet121_4xb256_in1k.py │ │ │ ├── densenet161_4xb256_in1k.py │ │ │ ├── densenet169_4xb256_in1k.py │ │ │ ├── densenet201_4xb256_in1k.py │ │ │ └── metafile.yml │ │ ├── dinov2 │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── vit-base-p14_dinov2-pre_headless.py │ │ │ ├── vit-giant-p14_dinov2-pre_headless.py │ │ │ ├── vit-large-p14_dinov2-pre_headless.py │ │ │ └── vit-small-p14_dinov2-pre_headless.py │ │ ├── edgenext │ │ │ ├── README.md │ │ │ ├── edgenext-base_8xb256-usi_in1k.py │ │ │ ├── edgenext-base_8xb256_in1k.py │ │ │ ├── edgenext-small_8xb256-usi_in1k.py │ │ │ ├── edgenext-small_8xb256_in1k.py │ │ │ ├── edgenext-xsmall_8xb256_in1k.py │ │ │ ├── edgenext-xxsmall_8xb256_in1k.py │ │ │ └── metafile.yml │ │ ├── efficientformer │ │ │ ├── README.md │ │ │ ├── efficientformer-l1_8xb128_in1k.py │ │ │ ├── efficientformer-l3_8xb128_in1k.py │ │ │ ├── efficientformer-l7_8xb128_in1k.py │ │ │ └── metafile.yml │ │ ├── efficientnet │ │ │ ├── README.md │ │ │ ├── efficientnet-b0_8xb32-01norm_in1k.py │ │ │ ├── efficientnet-b0_8xb32_in1k.py │ │ │ ├── efficientnet-b1_8xb32-01norm_in1k.py │ │ │ ├── efficientnet-b1_8xb32_in1k.py │ │ │ ├── efficientnet-b2_8xb32-01norm_in1k.py │ │ │ ├── efficientnet-b2_8xb32_in1k.py │ │ │ ├── efficientnet-b3_8xb32-01norm_in1k.py │ │ │ ├── efficientnet-b3_8xb32_in1k.py │ │ │ ├── efficientnet-b4_8xb32-01norm_in1k.py │ │ │ ├── efficientnet-b4_8xb32_in1k.py │ │ │ ├── efficientnet-b5_8xb32-01norm_in1k.py │ │ │ ├── efficientnet-b5_8xb32_in1k.py │ │ │ ├── efficientnet-b6_8xb32-01norm_in1k.py │ │ │ ├── efficientnet-b6_8xb32_in1k.py │ │ │ ├── efficientnet-b7_8xb32-01norm_in1k.py │ │ │ ├── efficientnet-b7_8xb32_in1k.py │ │ │ ├── efficientnet-b8_8xb32-01norm_in1k.py │ │ │ ├── efficientnet-b8_8xb32_in1k.py │ │ │ ├── efficientnet-em_8xb32-01norm_in1k.py │ │ │ ├── efficientnet-es_8xb32-01norm_in1k.py │ │ │ ├── efficientnet-l2_8xb32_in1k-475px.py │ │ │ ├── efficientnet-l2_8xb8_in1k-800px.py │ │ │ └── metafile.yml │ │ ├── efficientnet_v2 │ │ │ ├── README.md │ │ │ ├── efficientnetv2-b0_8xb32_in1k.py │ │ │ ├── efficientnetv2-b1_8xb32_in1k.py │ │ │ ├── efficientnetv2-b2_8xb32_in1k.py │ │ │ ├── efficientnetv2-b3_8xb32_in1k.py │ │ │ ├── efficientnetv2-l_8xb32_in1k-480px.py │ │ │ ├── efficientnetv2-l_8xb32_in21k.py │ │ │ ├── efficientnetv2-m_8xb32_in1k-480px.py │ │ │ ├── efficientnetv2-m_8xb32_in21k.py │ │ │ ├── efficientnetv2-s_8xb32_in1k-384px.py │ │ │ ├── efficientnetv2-s_8xb32_in21k.py │ │ │ ├── efficientnetv2-xl_8xb32_in1k-512px.py │ │ │ ├── efficientnetv2-xl_8xb32_in21k.py │ │ │ └── metafile.yml │ │ ├── eva │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ ├── vit-base-p16_8xb128-coslr-100e_in1k.py │ │ │ │ └── vit-base-p16_8xb2048-linear-coslr-100e_in1k.py │ │ │ ├── eva-g-p14_8xb16_in1k-336px.py │ │ │ ├── eva-g-p14_8xb16_in1k-560px.py │ │ │ ├── eva-g-p14_headless.py │ │ │ ├── eva-g-p16_headless.py │ │ │ ├── eva-l-p14_8xb16_in1k-196px.py │ │ │ ├── eva-l-p14_8xb16_in1k-336px.py │ │ │ ├── eva-l-p14_headless.py │ │ │ ├── eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k.py │ │ │ └── metafile.yml │ │ ├── eva02 │ │ │ ├── README.md │ │ │ ├── eva02-base-p14_headless.py │ │ │ ├── eva02-base-p14_in1k.py │ │ │ ├── eva02-large-p14_headless.py │ │ │ ├── eva02-large-p14_in1k.py │ │ │ ├── eva02-small-p14_headless.py │ │ │ ├── eva02-small-p14_in1k.py │ │ │ ├── eva02-tiny-p14_headless.py │ │ │ ├── eva02-tiny-p14_in1k.py │ │ │ └── metafile.yml │ │ ├── flamingo │ │ │ ├── README.md │ │ │ ├── flamingo_fewshot_caption.py │ │ │ ├── flamingo_fewshot_vqa.py │ │ │ ├── flamingo_zeroshot_caption.py │ │ │ ├── flamingo_zeroshot_vqa.py │ │ │ └── metafile.yml │ │ ├── glip │ │ │ ├── README.md │ │ │ ├── glip-l_headless.py │ │ │ ├── glip-t_headless.py │ │ │ └── metafile.yml │ │ ├── hivit │ │ │ ├── README.md │ │ │ ├── hivit-base-p16_16xb64_in1k.py │ │ │ ├── hivit-small-p16_16xb64_in1k.py │ │ │ ├── hivit-tiny-p16_16xb64_in1k.py │ │ │ └── metafile.yml │ │ ├── hornet │ │ │ ├── README.md │ │ │ ├── hornet-base-gf_8xb64_in1k.py │ │ │ ├── hornet-base_8xb64_in1k.py │ │ │ ├── hornet-small-gf_8xb64_in1k.py │ │ │ ├── hornet-small_8xb64_in1k.py │ │ │ ├── hornet-tiny-gf_8xb128_in1k.py │ │ │ ├── hornet-tiny_8xb128_in1k.py │ │ │ └── metafile.yml │ │ ├── hrnet │ │ │ ├── README.md │ │ │ ├── hrnet-w18_4xb32_in1k.py │ │ │ ├── hrnet-w30_4xb32_in1k.py │ │ │ ├── hrnet-w32_4xb32_in1k.py │ │ │ ├── hrnet-w40_4xb32_in1k.py │ │ │ ├── hrnet-w44_4xb32_in1k.py │ │ │ ├── hrnet-w48_4xb32_in1k.py │ │ │ ├── hrnet-w64_4xb32_in1k.py │ │ │ └── metafile.yml │ │ ├── inception_v3 │ │ │ ├── README.md │ │ │ ├── inception-v3_8xb32_in1k.py │ │ │ └── metafile.yml │ │ ├── itpn │ │ │ ├── README.md │ │ │ ├── itpn-clip-b_hivit-base-p16_8xb256-amp-coslr-300e_in1k.py │ │ │ ├── itpn-clip-b_hivit-base-p16_8xb256-amp-coslr-800e_in1k.py │ │ │ ├── itpn-pixel_hivit-base-p16_8xb512-amp-coslr-1600e_in1k.py │ │ │ ├── itpn-pixel_hivit-base-p16_8xb512-amp-coslr-400e_in1k.py │ │ │ ├── itpn-pixel_hivit-base-p16_8xb512-amp-coslr-800e_in1k.py │ │ │ ├── itpn-pixel_hivit-large-p16_8xb512-amp-coslr-1600e_in1k.py │ │ │ ├── itpn-pixel_hivit-large-p16_8xb512-amp-coslr-400e_in1k.py │ │ │ ├── itpn-pixel_hivit-large-p16_8xb512-amp-coslr-800e_in1k.py │ │ │ └── metafile.yml │ │ ├── lenet │ │ │ ├── README.md │ │ │ └── lenet5_mnist.py │ │ ├── levit │ │ │ ├── README.md │ │ │ ├── deploy │ │ │ │ ├── levit-128_8xb256_in1k.py │ │ │ │ ├── levit-128s_8xb256_in1k.py │ │ │ │ ├── levit-192_8xb256_in1k.py │ │ │ │ ├── levit-256_8xb256_in1k.py │ │ │ │ └── levit-384_8xb256_in1k.py │ │ │ ├── levit-128_8xb256_in1k.py │ │ │ ├── levit-128s_8xb256_in1k.py │ │ │ ├── levit-192_8xb256_in1k.py │ │ │ ├── levit-256_8xb256_in1k.py │ │ │ ├── levit-384_8xb256_in1k.py │ │ │ └── metafile.yml │ │ ├── llava │ │ │ ├── README.md │ │ │ ├── llava-7b-v1_caption.py │ │ │ └── metafile.yml │ │ ├── mae │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ ├── vit-base-p16_8xb128-coslr-100e_in1k.py │ │ │ │ ├── vit-base-p16_8xb2048-linear-coslr-90e_in1k.py │ │ │ │ ├── vit-huge-p14_32xb8-coslr-50e_in1k-448px.py │ │ │ │ ├── vit-huge-p14_8xb128-coslr-50e_in1k.py │ │ │ │ ├── vit-huge-p14_8xb128-ds-coslr-50e_in1k.py │ │ │ │ ├── vit-huge-p14_8xb128-fsdp-coslr-50e_in1k.py │ │ │ │ ├── vit-large-p16_8xb128-coslr-50e_in1k.py │ │ │ │ ├── vit-large-p16_8xb128-ds-coslr-50e_in1k.py │ │ │ │ ├── vit-large-p16_8xb128-fsdp-coslr-50e_in1k.py │ │ │ │ └── vit-large-p16_8xb2048-linear-coslr-90e_in1k.py │ │ │ ├── mae_hivit-base-p16_8xb512-amp-coslr-1600e_in1k.py │ │ │ ├── mae_hivit-base-p16_8xb512-amp-coslr-400e_in1k.py │ │ │ ├── mae_hivit-base-p16_8xb512-amp-coslr-800e_in1k.py │ │ │ ├── mae_hivit-large-p16_8xb512-amp-coslr-1600e_in1k.py │ │ │ ├── mae_hivit-large-p16_8xb512-amp-coslr-400e_in1k.py │ │ │ ├── mae_hivit-large-p16_8xb512-amp-coslr-800e_in1k.py │ │ │ ├── mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py │ │ │ ├── mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py │ │ │ ├── mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py │ │ │ ├── mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py │ │ │ ├── mae_vit-huge-p14_8xb512-amp-coslr-1600e_in1k.py │ │ │ ├── mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py │ │ │ ├── mae_vit-large-p16_8xb512-amp-coslr-300e_in1k.py │ │ │ ├── mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py │ │ │ ├── mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py │ │ │ └── metafile.yml │ │ ├── maskfeat │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ └── vit-base-p16_8xb256-coslr-100e_in1k.py │ │ │ ├── maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k.py │ │ │ └── metafile.yml │ │ ├── mff │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ ├── vit-base-p16_8xb128-coslr-100e_in1k.py │ │ │ │ └── vit-base-p16_8xb2048-linear-coslr-90e_in1k.py │ │ │ ├── metafile.yml │ │ │ ├── mff_vit-base-p16_8xb512-amp-coslr-300e_in1k.py │ │ │ └── mff_vit-base-p16_8xb512-amp-coslr-800e_in1k.py │ │ ├── milan │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ ├── vit-base-p16_8xb128-coslr-100e_in1k.py │ │ │ │ └── vit-base-p16_8xb2048-linear-coslr-100e_in1k.py │ │ │ ├── metafile.yml │ │ │ └── milan_vit-base-p16_16xb256-amp-coslr-400e_in1k.py │ │ ├── minigpt4 │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── minigpt-4_baichuan-7b_caption.py │ │ │ └── minigpt-4_vicuna-7b_caption.py │ │ ├── mixmim │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ ├── mixmim-base_8xb128-coslr-100e_in1k.py │ │ │ │ └── mixmim-base_8xb64_in1k.py │ │ │ ├── metafile.yml │ │ │ └── mixmim_mixmim-base_16xb128-coslr-300e_in1k.py │ │ ├── mlp_mixer │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── mlp-mixer-base-p16_64xb64_in1k.py │ │ │ └── mlp-mixer-large-p16_64xb64_in1k.py │ │ ├── mobilenet_v2 │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ └── mobilenet-v2_8xb32_in1k.py │ │ ├── mobilenet_v3 │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── mobilenet-v3-large_8xb128_in1k.py │ │ │ ├── mobilenet-v3-small-050_8xb128_in1k.py │ │ │ ├── mobilenet-v3-small-075_8xb128_in1k.py │ │ │ ├── mobilenet-v3-small_8xb128_in1k.py │ │ │ └── mobilenet-v3-small_8xb16_cifar10.py │ │ ├── mobileone │ │ │ ├── README.md │ │ │ ├── deploy │ │ │ │ ├── mobileone-s0_deploy_8xb32_in1k.py │ │ │ │ ├── mobileone-s1_deploy_8xb32_in1k.py │ │ │ │ ├── mobileone-s2_deploy_8xb32_in1k.py │ │ │ │ ├── mobileone-s3_deploy_8xb32_in1k.py │ │ │ │ └── mobileone-s4_deploy_8xb32_in1k.py │ │ │ ├── metafile.yml │ │ │ ├── mobileone-s0_8xb32_in1k.py │ │ │ ├── mobileone-s1_8xb32_in1k.py │ │ │ ├── mobileone-s2_8xb32_in1k.py │ │ │ ├── mobileone-s3_8xb32_in1k.py │ │ │ └── mobileone-s4_8xb32_in1k.py │ │ ├── mobilevit │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── mobilevit-small_8xb128_in1k.py │ │ │ ├── mobilevit-xsmall_8xb128_in1k.py │ │ │ └── mobilevit-xxsmall_8xb128_in1k.py │ │ ├── mocov2 │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ └── resnet50_8xb32-linear-steplr-100e_in1k.py │ │ │ ├── metafile.yml │ │ │ └── mocov2_resnet50_8xb32-coslr-200e_in1k.py │ │ ├── mocov3 │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ ├── resnet50_8xb128-linear-coslr-90e_in1k.py │ │ │ │ ├── vit-base-p16_8xb128-linear-coslr-90e_in1k.py │ │ │ │ ├── vit-base-p16_8xb64-coslr-150e_in1k.py │ │ │ │ ├── vit-large-p16_8xb64-coslr-100e_in1k.py │ │ │ │ └── vit-small-p16_8xb128-linear-coslr-90e_in1k.py │ │ │ ├── metafile.yml │ │ │ ├── mocov3_resnet50_8xb512-amp-coslr-100e_in1k.py │ │ │ ├── mocov3_resnet50_8xb512-amp-coslr-300e_in1k.py │ │ │ ├── mocov3_resnet50_8xb512-amp-coslr-800e_in1k.py │ │ │ ├── mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k.py │ │ │ ├── mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k.py │ │ │ └── mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k.py │ │ ├── mvit │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── mvitv2-base_8xb256_in1k.py │ │ │ ├── mvitv2-large_8xb256_in1k.py │ │ │ ├── mvitv2-small_8xb256_in1k.py │ │ │ └── mvitv2-tiny_8xb256_in1k.py │ │ ├── ofa │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── ofa-base_finetuned_caption.py │ │ │ ├── ofa-base_finetuned_refcoco.py │ │ │ ├── ofa-base_finetuned_vqa.py │ │ │ ├── ofa-base_zeroshot_vqa.py │ │ │ └── ofa-large_zeroshot_vqa.py │ │ ├── otter │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── otter-9b_caption.py │ │ │ └── otter-9b_vqa.py │ │ ├── poolformer │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── poolformer-m36_32xb128_in1k.py │ │ │ ├── poolformer-m48_32xb128_in1k.py │ │ │ ├── poolformer-s12_32xb128_in1k.py │ │ │ ├── poolformer-s24_32xb128_in1k.py │ │ │ └── poolformer-s36_32xb128_in1k.py │ │ ├── regnet │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── regnetx-1.6gf_8xb128_in1k.py │ │ │ ├── regnetx-12gf_8xb64_in1k.py │ │ │ ├── regnetx-3.2gf_8xb64_in1k.py │ │ │ ├── regnetx-4.0gf_8xb64_in1k.py │ │ │ ├── regnetx-400mf_8xb128_in1k.py │ │ │ ├── regnetx-6.4gf_8xb64_in1k.py │ │ │ ├── regnetx-8.0gf_8xb64_in1k.py │ │ │ └── regnetx-800mf_8xb128_in1k.py │ │ ├── replknet │ │ │ ├── README.md │ │ │ ├── deploy │ │ │ │ ├── replknet-31B-deploy_32xb64_in1k-384px.py │ │ │ │ ├── replknet-31B-deploy_32xb64_in1k.py │ │ │ │ ├── replknet-31L-deploy_32xb64_in1k-384px.py │ │ │ │ └── replknet-XL-deploy_32xb64_in1k-320px.py │ │ │ ├── metafile.yml │ │ │ ├── replknet-31B_32xb64_in1k-384px.py │ │ │ ├── replknet-31B_32xb64_in1k.py │ │ │ ├── replknet-31L_32xb64_in1k-384px.py │ │ │ └── replknet-XL_32xb64_in1k-320px.py │ │ ├── repmlp │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── repmlp-base_8xb64_in1k-256px.py │ │ │ ├── repmlp-base_8xb64_in1k.py │ │ │ ├── repmlp-base_delopy_8xb64_in1k.py │ │ │ └── repmlp-base_deploy_8xb64_in1k-256px.py │ │ ├── repvgg │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── repvgg-A0_8xb32_in1k.py │ │ │ ├── repvgg-A0_deploy_in1k.py │ │ │ ├── repvgg-A1_8xb32_in1k.py │ │ │ ├── repvgg-A2_8xb32_in1k.py │ │ │ ├── repvgg-B0_8xb32_in1k.py │ │ │ ├── repvgg-B1_8xb32_in1k.py │ │ │ ├── repvgg-B1g2_8xb32_in1k.py │ │ │ ├── repvgg-B1g4_8xb32_in1k.py │ │ │ ├── repvgg-B2_8xb32_in1k.py │ │ │ ├── repvgg-B2g4_8xb32_in1k.py │ │ │ ├── repvgg-B3_8xb32_in1k.py │ │ │ ├── repvgg-B3g4_8xb32_in1k.py │ │ │ └── repvgg-D2se_8xb32_in1k.py │ │ ├── res2net │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── res2net101-w26-s4_8xb32_in1k.py │ │ │ ├── res2net50-w14-s8_8xb32_in1k.py │ │ │ └── res2net50-w26-s8_8xb32_in1k.py │ │ ├── resnest │ │ │ ├── README.md │ │ │ ├── _randaug_policies.py │ │ │ ├── resnest101_32xb64_in1k.py │ │ │ ├── resnest200_64xb32_in1k.py │ │ │ ├── resnest269_64xb32_in1k.py │ │ │ └── resnest50_32xb64_in1k.py │ │ ├── resnet │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── resnet101_8xb16_cifar10.py │ │ │ ├── resnet101_8xb32_in1k.py │ │ │ ├── resnet152_8xb16_cifar10.py │ │ │ ├── resnet152_8xb32_in1k.py │ │ │ ├── resnet18_8xb16_cifar10.py │ │ │ ├── resnet18_8xb32_in1k.py │ │ │ ├── resnet34_8xb16_cifar10.py │ │ │ ├── resnet34_8xb32_in1k.py │ │ │ ├── resnet50_32xb64-warmup-coslr_in1k.py │ │ │ ├── resnet50_32xb64-warmup-lbs_in1k.py │ │ │ ├── resnet50_32xb64-warmup_in1k.py │ │ │ ├── resnet50_8xb128_coslr-90e_in21k.py │ │ │ ├── resnet50_8xb16-mixup_cifar10.py │ │ │ ├── resnet50_8xb16_cifar10.py │ │ │ ├── resnet50_8xb16_cifar100.py │ │ │ ├── resnet50_8xb256-rsb-a1-600e_in1k.py │ │ │ ├── resnet50_8xb256-rsb-a2-300e_in1k.py │ │ │ ├── resnet50_8xb256-rsb-a3-100e_in1k.py │ │ │ ├── resnet50_8xb32-coslr-preciseBN_in1k.py │ │ │ ├── resnet50_8xb32-coslr_in1k.py │ │ │ ├── resnet50_8xb32-cutmix_in1k.py │ │ │ ├── resnet50_8xb32-fp16-dynamic_in1k.py │ │ │ ├── resnet50_8xb32-fp16_in1k.py │ │ │ ├── resnet50_8xb32-lbs_in1k.py │ │ │ ├── resnet50_8xb32-mixup_in1k.py │ │ │ ├── resnet50_8xb32_in1k.py │ │ │ ├── resnet50_8xb8_cub.py │ │ │ ├── resnetv1c101_8xb32_in1k.py │ │ │ ├── resnetv1c152_8xb32_in1k.py │ │ │ ├── resnetv1c50_8xb32_in1k.py │ │ │ ├── resnetv1d101_8xb32_in1k.py │ │ │ ├── resnetv1d152_8xb32_in1k.py │ │ │ └── resnetv1d50_8xb32_in1k.py │ │ ├── resnext │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── resnext101-32x4d_8xb32_in1k.py │ │ │ ├── resnext101-32x8d_8xb32_in1k.py │ │ │ ├── resnext152-32x4d_8xb32_in1k.py │ │ │ └── resnext50-32x4d_8xb32_in1k.py │ │ ├── revvit │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── revvit-base_8xb256_in1k.py │ │ │ └── revvit-small_8xb256_in1k.py │ │ ├── riformer │ │ │ ├── README.md │ │ │ ├── deploy │ │ │ │ ├── riformer-m36-deploy_8xb128_in1k.py │ │ │ │ ├── riformer-m36-deploy_8xb64_in1k-384px.py │ │ │ │ ├── riformer-m48-deploy_8xb64_in1k-384px.py │ │ │ │ ├── riformer-m48-deploy_8xb64_in1k.py │ │ │ │ ├── riformer-s12-deploy_8xb128_in1k-384px.py │ │ │ │ ├── riformer-s12-deploy_8xb128_in1k.py │ │ │ │ ├── riformer-s24-deploy_8xb128_in1k-384px.py │ │ │ │ ├── riformer-s24-deploy_8xb128_in1k.py │ │ │ │ ├── riformer-s36-deploy_8xb128_in1k.py │ │ │ │ └── riformer-s36-deploy_8xb64_in1k-384px.py │ │ │ ├── metafile.yml │ │ │ ├── riformer-m36_8xb128_in1k.py │ │ │ ├── riformer-m36_8xb64_in1k-384px.py │ │ │ ├── riformer-m48_8xb64_in1k-384px.py │ │ │ ├── riformer-m48_8xb64_in1k.py │ │ │ ├── riformer-s12_8xb128_in1k-384px.py │ │ │ ├── riformer-s12_8xb128_in1k.py │ │ │ ├── riformer-s24_8xb128_in1k-384px.py │ │ │ ├── riformer-s24_8xb128_in1k.py │ │ │ ├── riformer-s36_8xb128_in1k.py │ │ │ └── riformer-s36_8xb64_in1k-384px.py │ │ ├── sam │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── vit-base-p16_sam_headless.py │ │ │ ├── vit-huge-p16_sam_headless.py │ │ │ └── vit-large-p16_sam_headless.py │ │ ├── seresnet │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── seresnet101_8xb32_in1k.py │ │ │ ├── seresnet50_8xb32_in1k.py │ │ │ ├── seresnext101-32x4d_8xb32_in1k.py │ │ │ └── seresnext50-32x4d_8xb32_in1k.py │ │ ├── shufflenet_v1 │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ └── shufflenet-v1-1x_16xb64_in1k.py │ │ ├── shufflenet_v2 │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ └── shufflenet-v2-1x_16xb64_in1k.py │ │ ├── simclr │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ └── resnet50_8xb512-linear-coslr-90e_in1k.py │ │ │ ├── metafile.yml │ │ │ ├── simclr_resnet50_16xb256-coslr-200e_in1k.py │ │ │ ├── simclr_resnet50_16xb256-coslr-800e_in1k.py │ │ │ └── simclr_resnet50_8xb32-coslr-200e_in1k.py │ │ ├── simmim │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ ├── swin-base-w6_8xb256-coslr-100e_in1k-192px.py │ │ │ │ ├── swin-base-w7_8xb256-coslr-100e_in1k.py │ │ │ │ └── swin-large-w14_8xb256-coslr-100e_in1k.py │ │ │ ├── metafile.yml │ │ │ ├── simmim_swin-base-w6_16xb128-amp-coslr-100e_in1k-192px.py │ │ │ ├── simmim_swin-base-w6_16xb128-amp-coslr-800e_in1k-192px.py │ │ │ ├── simmim_swin-base-w6_8xb256-amp-coslr-100e_in1k-192px.py │ │ │ └── simmim_swin-large-w12_16xb128-amp-coslr-800e_in1k-192px.py │ │ ├── simsiam │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ └── resnet50_8xb512-linear-coslr-90e_in1k.py │ │ │ ├── metafile.yml │ │ │ ├── simsiam_resnet50_8xb32-coslr-100e_in1k.py │ │ │ └── simsiam_resnet50_8xb32-coslr-200e_in1k.py │ │ ├── spark │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ ├── convnextv2-tiny_8xb256-coslr-300e_in1k.py │ │ │ │ └── resnet50_8xb256-coslr-300e_in1k.py │ │ │ ├── metafile.yml │ │ │ ├── spark_sparse-convnext-small_16xb256-amp-coslr-800e_in1k.py │ │ │ ├── spark_sparse-convnextv2-tiny_16xb256-amp-coslr-800e_in1k.py │ │ │ ├── spark_sparse-resnet50_8xb512-amp-coslr-1600e_in1k.py │ │ │ └── spark_sparse-resnet50_8xb512-amp-coslr-800e_in1k.py │ │ ├── swav │ │ │ ├── README.md │ │ │ ├── benchmarks │ │ │ │ └── resnet50_8xb512-linear-coslr-90e_in1k.py │ │ │ ├── metafile.yml │ │ │ └── swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px.py │ │ ├── swin_transformer │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── swin-base_16xb64_in1k-384px.py │ │ │ ├── swin-base_16xb64_in1k.py │ │ │ ├── swin-large_16xb64_in1k-384px.py │ │ │ ├── swin-large_16xb64_in1k.py │ │ │ ├── swin-large_8xb8_cub-384px.py │ │ │ ├── swin-small_16xb64_in1k.py │ │ │ └── swin-tiny_16xb64_in1k.py │ │ ├── swin_transformer_v2 │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── swinv2-base-w12_8xb128_in21k-192px.py │ │ │ ├── swinv2-base-w16_16xb64_in1k-256px.py │ │ │ ├── swinv2-base-w16_in21k-pre_16xb64_in1k-256px.py │ │ │ ├── swinv2-base-w24_in21k-pre_16xb64_in1k-384px.py │ │ │ ├── swinv2-base-w8_16xb64_in1k-256px.py │ │ │ ├── swinv2-large-w12_8xb128_in21k-192px.py │ │ │ ├── swinv2-large-w16_in21k-pre_16xb64_in1k-256px.py │ │ │ ├── swinv2-large-w24_in21k-pre_16xb64_in1k-384px.py │ │ │ ├── swinv2-small-w16_16xb64_in1k-256px.py │ │ │ ├── swinv2-small-w8_16xb64_in1k-256px.py │ │ │ ├── swinv2-tiny-w16_16xb64_in1k-256px.py │ │ │ └── swinv2-tiny-w8_16xb64_in1k-256px.py │ │ ├── t2t_vit │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── t2t-vit-t-14_8xb64_in1k.py │ │ │ ├── t2t-vit-t-19_8xb64_in1k.py │ │ │ └── t2t-vit-t-24_8xb64_in1k.py │ │ ├── tinyvit │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── tinyvit-11m-distill_8xb256_in1k.py │ │ │ ├── tinyvit-11m_8xb256_in1k.py │ │ │ ├── tinyvit-21m-distill_8xb256_in1k-384px.py │ │ │ ├── tinyvit-21m-distill_8xb256_in1k-512px.py │ │ │ ├── tinyvit-21m-distill_8xb256_in1k.py │ │ │ ├── tinyvit-21m_8xb256_in1k.py │ │ │ ├── tinyvit-5m-distill_8xb256_in1k.py │ │ │ └── tinyvit-5m_8xb256_in1k.py │ │ ├── tnt │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ └── tnt-s-p16_16xb64_in1k.py │ │ ├── twins │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── twins-pcpvt-base_8xb128_in1k.py │ │ │ ├── twins-pcpvt-large_16xb64_in1k.py │ │ │ ├── twins-pcpvt-small_8xb128_in1k.py │ │ │ ├── twins-svt-base_8xb128_in1k.py │ │ │ ├── twins-svt-large_16xb64_in1k.py │ │ │ └── twins-svt-small_8xb128_in1k.py │ │ ├── van │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── van-base_8xb128_in1k.py │ │ │ ├── van-large_8xb128_in1k.py │ │ │ ├── van-small_8xb128_in1k.py │ │ │ └── van-tiny_8xb128_in1k.py │ │ ├── vgg │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── vgg11_8xb32_in1k.py │ │ │ ├── vgg11bn_8xb32_in1k.py │ │ │ ├── vgg13_8xb32_in1k.py │ │ │ ├── vgg13bn_8xb32_in1k.py │ │ │ ├── vgg16_8xb16_voc.py │ │ │ ├── vgg16_8xb32_in1k.py │ │ │ ├── vgg16bn_8xb32_in1k.py │ │ │ ├── vgg19_8xb32_in1k.py │ │ │ └── vgg19bn_8xb32_in1k.py │ │ ├── vig │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── pvig-base_8xb128_in1k.py │ │ │ ├── pvig-medium_8xb128_in1k.py │ │ │ ├── pvig-small_8xb128_in1k.py │ │ │ ├── pvig-tiny_8xb128_in1k.py │ │ │ ├── vig-base_8xb128_in1k.py │ │ │ ├── vig-small_8xb128_in1k.py │ │ │ └── vig-tiny_8xb128_in1k.py │ │ ├── vision_transformer │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── vit-base-p16_32xb128-mae_in1k.py │ │ │ ├── vit-base-p16_4xb544-ipu_in1k.py │ │ │ ├── vit-base-p16_64xb64_in1k-384px.py │ │ │ ├── vit-base-p16_64xb64_in1k.py │ │ │ ├── vit-base-p16_8xb64-lora_in1k-384px.py │ │ │ ├── vit-base-p32_64xb64_in1k-384px.py │ │ │ ├── vit-base-p32_64xb64_in1k.py │ │ │ ├── vit-large-p16_64xb64_in1k-384px.py │ │ │ ├── vit-large-p16_64xb64_in1k.py │ │ │ ├── vit-large-p32_64xb64_in1k-384px.py │ │ │ └── vit-large-p32_64xb64_in1k.py │ │ ├── wrn │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── wide-resnet101_8xb32_in1k.py │ │ │ ├── wide-resnet50_8xb32_in1k.py │ │ │ └── wide-resnet50_timm_8xb32_in1k.py │ │ └── xcit │ │ │ ├── README.md │ │ │ ├── metafile.yml │ │ │ ├── xcit-large-24-p16_8xb128_in1k-384px.py │ │ │ ├── xcit-large-24-p16_8xb128_in1k.py │ │ │ ├── xcit-large-24-p8_8xb128_in1k-384px.py │ │ │ ├── xcit-large-24-p8_8xb128_in1k.py │ │ │ ├── xcit-medium-24-p16_8xb128_in1k-384px.py │ │ │ ├── xcit-medium-24-p16_8xb128_in1k.py │ │ │ ├── xcit-medium-24-p8_8xb128_in1k-384px.py │ │ │ ├── xcit-medium-24-p8_8xb128_in1k.py │ │ │ ├── xcit-nano-12-p16_8xb128_in1k-384px.py │ │ │ ├── xcit-nano-12-p16_8xb128_in1k.py │ │ │ ├── xcit-nano-12-p8_8xb128_in1k-384px.py │ │ │ ├── xcit-nano-12-p8_8xb128_in1k.py │ │ │ ├── xcit-small-12-p16_8xb128_in1k-384px.py │ │ │ ├── xcit-small-12-p16_8xb128_in1k.py │ │ │ ├── xcit-small-12-p8_8xb128_in1k-384px.py │ │ │ ├── xcit-small-12-p8_8xb128_in1k.py │ │ │ ├── xcit-small-24-p16_8xb128_in1k-384px.py │ │ │ ├── xcit-small-24-p16_8xb128_in1k.py │ │ │ ├── xcit-small-24-p8_8xb128_in1k-384px.py │ │ │ ├── xcit-small-24-p8_8xb128_in1k.py │ │ │ ├── xcit-tiny-12-p16_8xb128_in1k-384px.py │ │ │ ├── xcit-tiny-12-p16_8xb128_in1k.py │ │ │ ├── xcit-tiny-12-p8_8xb128_in1k-384px.py │ │ │ ├── xcit-tiny-12-p8_8xb128_in1k.py │ │ │ ├── xcit-tiny-24-p16_8xb128_in1k-384px.py │ │ │ ├── xcit-tiny-24-p16_8xb128_in1k.py │ │ │ ├── xcit-tiny-24-p8_8xb128_in1k-384px.py │ │ │ └── xcit-tiny-24-p8_8xb128_in1k.py │ └── readme.md ├── tp.py └── utils.py ├── assets ├── activation_map.png ├── architecture.png ├── attn.png ├── detailed_updates.md ├── erf.png ├── get_started.md ├── performance.md └── ss2d.png ├── checks.sh ├── classification ├── config.py ├── configs │ ├── vssm │ │ ├── vmambav0_base_224.yaml │ │ ├── vmambav0_small_224.yaml │ │ ├── vmambav0_tiny_224.yaml │ │ ├── vmambav2_base_224.yaml │ │ ├── vmambav2_small_224.yaml │ │ ├── vmambav2_tiny_224.yaml │ │ ├── vmambav2v_base_224.yaml │ │ ├── vmambav2v_small_224.yaml │ │ └── vmambav2v_tiny_224.yaml │ ├── vssmab │ │ ├── vmambav0_tiny_224_a0.yaml │ │ ├── vmambav0_tiny_224_a01.yaml │ │ ├── vmambav0_tiny_224_a0seq.yaml │ │ ├── vmambav0_tiny_224_a1.yaml │ │ ├── vmambav0_tiny_224_a2.yaml │ │ ├── vmambav0_tiny_224_a3.yaml │ │ ├── vmambav0_tiny_224_a7.yaml │ │ ├── vmambav0_tiny_224_a7a.yaml │ │ ├── vmambav0_tiny_224_a8.yaml │ │ ├── vmambav2_tiny_224_a9d.yaml │ │ ├── vmambav2_tiny_224_bidi.yaml │ │ ├── vmambav2_tiny_224_bidi_ndw.yaml │ │ ├── vmambav2_tiny_224_cas2d.yaml │ │ ├── vmambav2_tiny_224_cas2d_ndw.yaml │ │ ├── vmambav2_tiny_224_ds16.yaml │ │ ├── vmambav2_tiny_224_ds2.yaml │ │ ├── vmambav2_tiny_224_ds4.yaml │ │ ├── vmambav2_tiny_224_ds8.yaml │ │ ├── vmambav2_tiny_224_gelu.yaml │ │ ├── vmambav2_tiny_224_init1.yaml │ │ ├── vmambav2_tiny_224_init2.yaml │ │ ├── vmambav2_tiny_224_m2s2h.yaml │ │ ├── vmambav2_tiny_224_m3s1h.yaml │ │ ├── vmambav2_tiny_224_ndw.yaml │ │ ├── vmambav2_tiny_224_ondw.yaml │ │ ├── vmambav2_tiny_224_onone.yaml │ │ ├── vmambav2_tiny_224_onsoftmax.yaml │ │ ├── vmambav2_tiny_224_posndw.yaml │ │ ├── vmambav2_tiny_224_relu.yaml │ │ ├── vmambav2_tiny_224_sr1hl5.yaml │ │ ├── vmambav2_tiny_224_sr1l5.yaml │ │ ├── vmambav2_tiny_224_unidi.yaml │ │ └── vmambav2_tiny_224_unidi_ndw.yaml │ └── wasted │ │ ├── vssm01 │ │ ├── vmambav2_tiny_224.yaml │ │ ├── vssm_base_224_a0.yaml │ │ ├── vssm_base_224_a6.yaml │ │ ├── vssm_base_224_aav1.yaml │ │ ├── vssm_base_224_ahv1_0423.yaml │ │ ├── vssm_base_224_ahv3.yaml │ │ ├── vssm_small_224_a0.yaml │ │ ├── vssm_small_224_a6.yaml │ │ ├── vssm_small_224_aav1.yaml │ │ ├── vssm_small_224_ahv3.yaml │ │ ├── vssm_tiny_224_a9v1.yaml │ │ ├── vssm_tiny_224_a9v2.yaml │ │ ├── vssm_tiny_224_a9v3.yaml │ │ ├── vssm_tiny_224_aaa.yaml │ │ ├── vssm_tiny_224_aav1.yaml │ │ ├── vssm_tiny_224_aav2.yaml │ │ ├── vssm_tiny_224_abv2.yaml │ │ ├── vssm_tiny_224_abv3.yaml │ │ ├── vssm_tiny_224_abv4.yaml │ │ ├── vssm_tiny_224_aca.yaml │ │ ├── vssm_tiny_224_acv1.yaml │ │ ├── vssm_tiny_224_acv1_61.yaml │ │ ├── vssm_tiny_224_acv1_66.yaml │ │ ├── vssm_tiny_224_acv1_67.yaml │ │ ├── vssm_tiny_224_acv1_68.yaml │ │ ├── vssm_tiny_224_acv2.yaml │ │ ├── vssm_tiny_224_acv3.yaml │ │ ├── vssm_tiny_224_acv4.yaml │ │ ├── vssm_tiny_224_adv1_mini.yaml │ │ ├── vssm_tiny_224_adv1_mini2.yaml │ │ ├── vssm_tiny_224_ahv3_0420.yaml │ │ └── vssm_tiny_224_aiv1.yaml │ │ ├── vssm1 │ │ ├── vssm_base_224.yaml │ │ ├── vssm_mini_224.yaml │ │ ├── vssm_small_224.yaml │ │ ├── vssm_tiny_224.yaml │ │ └── vssm_tiny_224_0220.yaml │ │ ├── vssm_base_224_ahv1.yaml │ │ ├── vssm_base_224_ahv1_0421.yaml │ │ ├── vssm_base_224_ahv1_0422.yaml │ │ ├── vssm_base_224_aiv1.yaml │ │ ├── vssm_base_224_aiv1_dp06.yaml │ │ ├── vssm_small_224_ahv1.yaml │ │ ├── vssm_small_224_ahv1_0421.yaml │ │ ├── vssm_small_224_ahv1_0422.yaml │ │ ├── vssm_small_224_aiv1.yaml │ │ ├── vssm_small_224_aiv1_dp04.yaml │ │ ├── vssm_tiny_224_0211.yaml │ │ ├── vssm_tiny_224_0211v1.yaml │ │ ├── vssm_tiny_224_0212.yaml │ │ ├── vssm_tiny_224_0213.yaml │ │ ├── vssm_tiny_224_0215.yaml │ │ ├── vssm_tiny_224_0216.yaml │ │ ├── vssm_tiny_224_0217.yaml │ │ ├── vssm_tiny_224_0218.yaml │ │ ├── vssm_tiny_224_0219.yaml │ │ ├── vssm_tiny_224_0221.yaml │ │ ├── vssm_tiny_224_0222.yaml │ │ ├── vssm_tiny_224_0223.yaml │ │ ├── vssm_tiny_224_0224.yaml │ │ ├── vssm_tiny_224_0225.yaml │ │ ├── vssm_tiny_224_0229.yaml │ │ ├── vssm_tiny_224_0229flex.yaml │ │ ├── vssm_tiny_224_0230.yaml │ │ ├── vssm_tiny_224_0230ab1d.yaml │ │ ├── vssm_tiny_224_0230ab2d.yaml │ │ ├── vssm_tiny_224_0309.yaml │ │ ├── vssm_tiny_224_0310.yaml │ │ ├── vssm_tiny_224_0311.yaml │ │ ├── vssm_tiny_224_0312.yaml │ │ ├── vssm_tiny_224_0313.yaml │ │ ├── vssm_tiny_224_0314.yaml │ │ ├── vssm_tiny_224_0315.yaml │ │ ├── vssm_tiny_224_0316.yaml │ │ ├── vssm_tiny_224_0317.yaml │ │ ├── vssm_tiny_224_0318.2.yaml │ │ ├── vssm_tiny_224_0318.yaml │ │ ├── vssm_tiny_224_0319.yaml │ │ ├── vssm_tiny_224_0320.yaml │ │ ├── vssm_tiny_224_0321.yaml │ │ ├── vssm_tiny_224_0322.yaml │ │ ├── vssm_tiny_224_0323.yaml │ │ ├── vssm_tiny_224_0324.yaml │ │ ├── vssm_tiny_224_0325.yaml │ │ ├── vssm_tiny_224_0326.yaml │ │ ├── vssm_tiny_224_0327.yaml │ │ ├── vssm_tiny_224_1.yaml │ │ ├── vssm_tiny_224_1v1.yaml │ │ ├── vssm_tiny_224_a8d.yaml │ │ ├── vssm_tiny_224_a9.yaml │ │ ├── vssm_tiny_224_a9a.yaml │ │ ├── vssm_tiny_224_aa.yaml │ │ ├── vssm_tiny_224_abv1.yaml │ │ ├── vssm_tiny_224_acb.yaml │ │ ├── vssm_tiny_224_acv1_0401.yaml │ │ ├── vssm_tiny_224_acv1_0403.yaml │ │ ├── vssm_tiny_224_acv1_0405.yaml │ │ ├── vssm_tiny_224_acv1_0406.yaml │ │ ├── vssm_tiny_224_acv1_0407.yaml │ │ ├── vssm_tiny_224_acv1_0408.yaml │ │ ├── vssm_tiny_224_acv1_0409.yaml │ │ ├── vssm_tiny_224_acv1_0410.yaml │ │ ├── vssm_tiny_224_acv1_6.yaml │ │ ├── vssm_tiny_224_acv1_62.yaml │ │ ├── vssm_tiny_224_acv1_62_0415.yaml │ │ ├── vssm_tiny_224_acv1_63.yaml │ │ ├── vssm_tiny_224_acv1_64.yaml │ │ ├── vssm_tiny_224_acv1_65.yaml │ │ ├── vssm_tiny_224_adv1.yaml │ │ ├── vssm_tiny_224_adv1c.yaml │ │ ├── vssm_tiny_224_aev1.yaml │ │ ├── vssm_tiny_224_aev1c.yaml │ │ ├── vssm_tiny_224_afv1.yaml │ │ ├── vssm_tiny_224_agv1.yaml │ │ ├── vssm_tiny_224_ahv1.yaml │ │ ├── vssm_tiny_224_ahv3.yaml │ │ └── vssm_tiny_224_ahv3_0418.yaml ├── data │ ├── __init__.py │ ├── build.py │ ├── cached_image_folder.py │ ├── data_simmim_ft.py │ ├── data_simmim_pt.py │ ├── imagenet22k_dataset.py │ ├── map22kto1k.txt │ ├── samplers.py │ └── zipreader.py ├── main.py ├── models │ ├── __init__.py │ ├── csm_triton.py │ ├── csms6s.py │ ├── mamba2 │ │ ├── __init__.py │ │ ├── k_activations.py │ │ ├── layer_norm.py │ │ ├── layernorm_gated.py │ │ ├── selective_state_update.py │ │ ├── ssd_bmm.py │ │ ├── ssd_chunk_scan.py │ │ ├── ssd_chunk_state.py │ │ ├── ssd_combined.py │ │ ├── ssd_minimal.py │ │ └── ssd_state_passing.py │ ├── vmamba.py │ └── vmamba_checks.py ├── readme.md └── utils │ ├── cosine_lr.py │ ├── logger.py │ ├── lr_scheduler.py │ ├── optimizer.py │ └── utils.py ├── detection ├── configs │ ├── _base_ │ │ ├── datasets │ │ │ ├── ade20k_instance.py │ │ │ ├── ade20k_panoptic.py │ │ │ ├── ade20k_semantic.py │ │ │ ├── cityscapes_detection.py │ │ │ ├── cityscapes_instance.py │ │ │ ├── coco_caption.py │ │ │ ├── coco_detection.py │ │ │ ├── coco_instance.py │ │ │ ├── coco_instance_semantic.py │ │ │ ├── coco_panoptic.py │ │ │ ├── coco_semantic.py │ │ │ ├── deepfashion.py │ │ │ ├── dsdl.py │ │ │ ├── isaid_instance.py │ │ │ ├── lvis_v0.5_instance.py │ │ │ ├── lvis_v1_instance.py │ │ │ ├── mot_challenge.py │ │ │ ├── mot_challenge_det.py │ │ │ ├── mot_challenge_reid.py │ │ │ ├── objects365v1_detection.py │ │ │ ├── objects365v2_detection.py │ │ │ ├── openimages_detection.py │ │ │ ├── refcoco+.py │ │ │ ├── refcoco.py │ │ │ ├── refcocog.py │ │ │ ├── semi_coco_detection.py │ │ │ ├── v3det.py │ │ │ ├── voc0712.py │ │ │ ├── wider_face.py │ │ │ └── youtube_vis.py │ │ ├── default_runtime.py │ │ ├── models │ │ │ ├── cascade-mask-rcnn_r50_fpn.py │ │ │ ├── cascade-rcnn_r50_fpn.py │ │ │ ├── fast-rcnn_r50_fpn.py │ │ │ ├── faster-rcnn_r50-caffe-c4.py │ │ │ ├── faster-rcnn_r50-caffe-dc5.py │ │ │ ├── faster-rcnn_r50_fpn.py │ │ │ ├── mask-rcnn_r50-caffe-c4.py │ │ │ ├── mask-rcnn_r50_fpn.py │ │ │ ├── retinanet_r50_fpn.py │ │ │ ├── rpn_r50-caffe-c4.py │ │ │ ├── rpn_r50_fpn.py │ │ │ └── ssd300.py │ │ └── schedules │ │ │ ├── schedule_1x.py │ │ │ ├── schedule_20e.py │ │ │ └── schedule_2x.py │ ├── convnext │ │ ├── README.md │ │ ├── cascade-mask-rcnn_convnext-s-p4-w7_fpn_4conv1fc-giou_amp-ms-crop-3x_coco.py │ │ ├── cascade-mask-rcnn_convnext-t-p4-w7_fpn_4conv1fc-giou_amp-ms-crop-3x_coco.py │ │ ├── mask-rcnn_convnext-t-p4-w7_fpn_amp-ms-crop-3x_coco.py │ │ └── metafile.yml │ ├── mask_rcnn │ │ ├── README.md │ │ ├── mask-rcnn_r101-caffe_fpn_1x_coco.py │ │ ├── mask-rcnn_r101-caffe_fpn_ms-poly-3x_coco.py │ │ ├── mask-rcnn_r101_fpn_1x_coco.py │ │ ├── mask-rcnn_r101_fpn_2x_coco.py │ │ ├── mask-rcnn_r101_fpn_8xb8-amp-lsj-200e_coco.py │ │ ├── mask-rcnn_r101_fpn_ms-poly-3x_coco.py │ │ ├── mask-rcnn_r18_fpn_8xb8-amp-lsj-200e_coco.py │ │ ├── mask-rcnn_r50-caffe-c4_1x_coco.py │ │ ├── mask-rcnn_r50-caffe_fpn_1x_coco.py │ │ ├── mask-rcnn_r50-caffe_fpn_ms-1x_coco.py │ │ ├── mask-rcnn_r50-caffe_fpn_ms-poly-1x_coco.py │ │ ├── mask-rcnn_r50-caffe_fpn_ms-poly-2x_coco.py │ │ ├── mask-rcnn_r50-caffe_fpn_ms-poly-3x_coco.py │ │ ├── mask-rcnn_r50-caffe_fpn_poly-1x_coco_v1.py │ │ ├── mask-rcnn_r50_fpn_1x-wandb_coco.py │ │ ├── mask-rcnn_r50_fpn_1x_coco.py │ │ ├── mask-rcnn_r50_fpn_2x_coco.py │ │ ├── mask-rcnn_r50_fpn_8xb8-amp-lsj-200e_coco.py │ │ ├── mask-rcnn_r50_fpn_amp-1x_coco.py │ │ ├── mask-rcnn_r50_fpn_ms-poly-3x_coco.py │ │ ├── mask-rcnn_r50_fpn_poly-1x_coco.py │ │ ├── mask-rcnn_x101-32x4d_fpn_1x_coco.py │ │ ├── mask-rcnn_x101-32x4d_fpn_2x_coco.py │ │ ├── mask-rcnn_x101-32x4d_fpn_ms-poly-3x_coco.py │ │ ├── mask-rcnn_x101-32x8d_fpn_1x_coco.py │ │ ├── mask-rcnn_x101-32x8d_fpn_ms-poly-1x_coco.py │ │ ├── mask-rcnn_x101-32x8d_fpn_ms-poly-3x_coco.py │ │ ├── mask-rcnn_x101-64x4d_fpn_1x_coco.py │ │ ├── mask-rcnn_x101-64x4d_fpn_2x_coco.py │ │ ├── mask-rcnn_x101-64x4d_fpn_ms-poly_3x_coco.py │ │ └── metafile.yml │ ├── swin │ │ ├── README.md │ │ ├── mask-rcnn_swin-s-p4-w7_fpn_amp-ms-crop-3x_coco.py │ │ ├── mask-rcnn_swin-t-p4-w7_fpn_1x_coco.py │ │ ├── mask-rcnn_swin-t-p4-w7_fpn_amp-ms-crop-3x_coco.py │ │ ├── mask-rcnn_swin-t-p4-w7_fpn_ms-crop-3x_coco.py │ │ ├── metafile.yml │ │ └── retinanet_swin-t-p4-w7_fpn_1x_coco.py │ ├── vssm │ │ ├── mask_rcnn_vssm_fpn_coco_base.py │ │ ├── mask_rcnn_vssm_fpn_coco_small.py │ │ ├── mask_rcnn_vssm_fpn_coco_small_ms_3x.py │ │ ├── mask_rcnn_vssm_fpn_coco_tiny.py │ │ └── mask_rcnn_vssm_fpn_coco_tiny_ms_3x.py │ └── vssm1 │ │ ├── mask_rcnn_vssm_fpn_coco_base.py │ │ ├── mask_rcnn_vssm_fpn_coco_small.py │ │ ├── mask_rcnn_vssm_fpn_coco_small_ms_3x.py │ │ ├── mask_rcnn_vssm_fpn_coco_tiny.py │ │ ├── mask_rcnn_vssm_fpn_coco_tiny1.py │ │ ├── mask_rcnn_vssm_fpn_coco_tiny1_ms_3x.py │ │ └── mask_rcnn_vssm_fpn_coco_tiny_ms_3x.py ├── model.py ├── readme.md └── tools │ ├── analysis_tools │ ├── analyze_logs.py │ ├── analyze_results.py │ ├── benchmark.py │ ├── browse_dataset.py │ ├── coco_error_analysis.py │ ├── coco_occluded_separated_recall.py │ ├── confusion_matrix.py │ ├── eval_metric.py │ ├── fuse_results.py │ ├── get_flops.py │ ├── mot │ │ ├── browse_dataset.py │ │ ├── dist_mot_search.sh │ │ ├── mot_error_visualize.py │ │ ├── mot_param_search.py │ │ └── slurm_mot_search.sh │ ├── optimize_anchors.py │ ├── robustness_eval.py │ └── test_robustness.py │ ├── dataset_converters │ ├── ade20k2coco.py │ ├── cityscapes.py │ ├── coco_stuff164k.py │ ├── crowdhuman2coco.py │ ├── images2coco.py │ ├── mot2coco.py │ ├── mot2reid.py │ ├── pascal_voc.py │ ├── prepare_coco_semantic_annos_from_panoptic_annos.py │ ├── scripts │ │ ├── preprocess_coco2017.sh │ │ ├── preprocess_voc2007.sh │ │ └── preprocess_voc2012.sh │ └── youtubevis2coco.py │ ├── deployment │ ├── mmdet2torchserve.py │ ├── mmdet_handler.py │ └── test_torchserver.py │ ├── dist_test.sh │ ├── dist_test_tracking.sh │ ├── dist_train.sh │ ├── misc │ ├── download_dataset.py │ ├── gen_coco_panoptic_test_info.py │ ├── get_crowdhuman_id_hw.py │ ├── get_image_metas.py │ ├── print_config.py │ └── split_coco.py │ ├── model_converters │ ├── detectron2_to_mmdet.py │ ├── detectron2pytorch.py │ ├── detic_to_mmdet.py │ ├── glip_to_mmdet.py │ ├── groundingdino_to_mmdet.py │ ├── publish_model.py │ ├── regnet2mmdet.py │ ├── selfsup2mmdet.py │ ├── swinv1_to_mmdet.py │ ├── upgrade_model_version.py │ └── upgrade_ssd_version.py │ ├── slurm_test.sh │ ├── slurm_test_tracking.sh │ ├── slurm_train.sh │ ├── test.py │ ├── test_tracking.py │ └── train.py ├── kernels └── selective_scan │ ├── README.md │ ├── csrc │ └── selective_scan │ │ ├── cub_extra.cuh │ │ ├── cus │ │ ├── selective_scan.cpp │ │ ├── selective_scan_bwd_kernel.cuh │ │ ├── selective_scan_core_bwd.cu │ │ ├── selective_scan_core_fwd.cu │ │ └── selective_scan_fwd_kernel.cuh │ │ ├── cusoflex │ │ ├── selective_scan_bwd_kernel_oflex.cuh │ │ ├── selective_scan_core_bwd.cu │ │ ├── selective_scan_core_fwd.cu │ │ ├── selective_scan_fwd_kernel_oflex.cuh │ │ ├── selective_scan_oflex.cpp │ │ └── selective_scan_oflex.h │ │ ├── reverse_scan.cuh │ │ ├── selective_scan.h │ │ ├── selective_scan_common.h │ │ ├── static_switch.h │ │ └── uninitialized_copy.cuh │ ├── setup.py │ ├── test_selective_scan.py │ ├── test_selective_scan_easy.py │ └── test_selective_scan_speed.py ├── modelcard.sh ├── requirements.txt ├── segmentation ├── configs │ ├── _base_ │ │ ├── datasets │ │ │ ├── ade20k.py │ │ │ ├── ade20k_640x640.py │ │ │ ├── bdd100k.py │ │ │ ├── chase_db1.py │ │ │ ├── cityscapes.py │ │ │ ├── cityscapes_1024x1024.py │ │ │ ├── cityscapes_768x768.py │ │ │ ├── cityscapes_769x769.py │ │ │ ├── cityscapes_832x832.py │ │ │ ├── coco-stuff10k.py │ │ │ ├── coco-stuff164k.py │ │ │ ├── drive.py │ │ │ ├── hrf.py │ │ │ ├── isaid.py │ │ │ ├── levir_256x256.py │ │ │ ├── loveda.py │ │ │ ├── mapillary_v1.py │ │ │ ├── mapillary_v1_65.py │ │ │ ├── mapillary_v2.py │ │ │ ├── nyu.py │ │ │ ├── nyu_512x512.py │ │ │ ├── pascal_context.py │ │ │ ├── pascal_context_59.py │ │ │ ├── pascal_voc12.py │ │ │ ├── pascal_voc12_aug.py │ │ │ ├── potsdam.py │ │ │ ├── refuge.py │ │ │ ├── stare.py │ │ │ ├── synapse.py │ │ │ └── vaihingen.py │ │ ├── default_runtime.py │ │ ├── models │ │ │ ├── ann_r50-d8.py │ │ │ ├── apcnet_r50-d8.py │ │ │ ├── bisenetv1_r18-d32.py │ │ │ ├── bisenetv2.py │ │ │ ├── ccnet_r50-d8.py │ │ │ ├── cgnet.py │ │ │ ├── danet_r50-d8.py │ │ │ ├── deeplabv3_r50-d8.py │ │ │ ├── deeplabv3_unet_s5-d16.py │ │ │ ├── deeplabv3plus_r50-d8.py │ │ │ ├── dmnet_r50-d8.py │ │ │ ├── dnl_r50-d8.py │ │ │ ├── dpt_vit-b16.py │ │ │ ├── emanet_r50-d8.py │ │ │ ├── encnet_r50-d8.py │ │ │ ├── erfnet_fcn.py │ │ │ ├── fast_scnn.py │ │ │ ├── fastfcn_r50-d32_jpu_psp.py │ │ │ ├── fcn_hr18.py │ │ │ ├── fcn_r50-d8.py │ │ │ ├── fcn_unet_s5-d16.py │ │ │ ├── fpn_poolformer_s12.py │ │ │ ├── fpn_r50.py │ │ │ ├── gcnet_r50-d8.py │ │ │ ├── icnet_r50-d8.py │ │ │ ├── isanet_r50-d8.py │ │ │ ├── lraspp_m-v3-d8.py │ │ │ ├── nonlocal_r50-d8.py │ │ │ ├── ocrnet_hr18.py │ │ │ ├── ocrnet_r50-d8.py │ │ │ ├── pointrend_r50.py │ │ │ ├── psanet_r50-d8.py │ │ │ ├── pspnet_r50-d8.py │ │ │ ├── pspnet_unet_s5-d16.py │ │ │ ├── san_vit-b16.py │ │ │ ├── segformer_mit-b0.py │ │ │ ├── segmenter_vit-b16_mask.py │ │ │ ├── setr_mla.py │ │ │ ├── setr_naive.py │ │ │ ├── setr_pup.py │ │ │ ├── stdc.py │ │ │ ├── twins_pcpvt-s_fpn.py │ │ │ ├── twins_pcpvt-s_upernet.py │ │ │ ├── upernet_beit.py │ │ │ ├── upernet_convnext.py │ │ │ ├── upernet_mae.py │ │ │ ├── upernet_r50.py │ │ │ ├── upernet_swin.py │ │ │ ├── upernet_vit-b16_ln_mln.py │ │ │ └── vpd_sd.py │ │ └── schedules │ │ │ ├── schedule_160k.py │ │ │ ├── schedule_20k.py │ │ │ ├── schedule_240k.py │ │ │ ├── schedule_25k.py │ │ │ ├── schedule_320k.py │ │ │ ├── schedule_40k.py │ │ │ └── schedule_80k.py │ ├── convnext │ │ ├── README.md │ │ ├── convnext-base_upernet_8xb2-amp-160k_ade20k-512x512.py │ │ ├── convnext-base_upernet_8xb2-amp-160k_ade20k-640x640.py │ │ ├── convnext-large_upernet_8xb2-amp-160k_ade20k-640x640.py │ │ ├── convnext-small_upernet_8xb2-amp-160k_ade20k-512x512.py │ │ ├── convnext-tiny_upernet_8xb2-amp-160k_ade20k-512x512.py │ │ ├── convnext-xlarge_upernet_8xb2-amp-160k_ade20k-640x640.py │ │ └── metafile.yaml │ ├── swin │ │ ├── README.md │ │ ├── metafile.yaml │ │ ├── swin-base-patch4-window12-in1k-384x384-pre_upernet_8xb2-160k_ade20k-512x512.py │ │ ├── swin-base-patch4-window12-in22k-384x384-pre_upernet_8xb2-160k_ade20k-512x512.py │ │ ├── swin-base-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py │ │ ├── swin-base-patch4-window7-in22k-pre_upernet_8xb2-160k_ade20k-512x512.py │ │ ├── swin-large-patch4-window12-in22k-384x384-pre_upernet_8xb2-160k_ade20k-512x512.py │ │ ├── swin-large-patch4-window7-in22k-pre_upernet_8xb2-160k_ade20k-512x512.py │ │ ├── swin-small-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py │ │ ├── swin-tiny-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py │ │ └── swin-tiny-patch4-window7_upernet_1xb8-20k_levir-256x256.py │ ├── upernet │ │ ├── README.md │ │ ├── metafile.yaml │ │ ├── upernet_r101_4xb2-40k_cityscapes-512x1024.py │ │ ├── upernet_r101_4xb2-40k_cityscapes-769x769.py │ │ ├── upernet_r101_4xb2-80k_cityscapes-512x1024.py │ │ ├── upernet_r101_4xb2-80k_cityscapes-769x769.py │ │ ├── upernet_r101_4xb4-160k_ade20k-512x512.py │ │ ├── upernet_r101_4xb4-20k_voc12aug-512x512.py │ │ ├── upernet_r101_4xb4-40k_voc12aug-512x512.py │ │ ├── upernet_r101_4xb4-80k_ade20k-512x512.py │ │ ├── upernet_r18_4xb2-40k_cityscapes-512x1024.py │ │ ├── upernet_r18_4xb2-80k_cityscapes-512x1024.py │ │ ├── upernet_r18_4xb4-160k_ade20k-512x512.py │ │ ├── upernet_r18_4xb4-20k_voc12aug-512x512.py │ │ ├── upernet_r18_4xb4-40k_voc12aug-512x512.py │ │ ├── upernet_r18_4xb4-80k_ade20k-512x512.py │ │ ├── upernet_r50_4xb2-40k_cityscapes-512x1024.py │ │ ├── upernet_r50_4xb2-40k_cityscapes-769x769.py │ │ ├── upernet_r50_4xb2-80k_cityscapes-512x1024.py │ │ ├── upernet_r50_4xb2-80k_cityscapes-769x769.py │ │ ├── upernet_r50_4xb4-160k_ade20k-512x512.py │ │ ├── upernet_r50_4xb4-20k_voc12aug-512x512.py │ │ ├── upernet_r50_4xb4-40k_voc12aug-512x512.py │ │ └── upernet_r50_4xb4-80k_ade20k-512x512.py │ ├── vit │ │ ├── README.md │ │ ├── metafile.yaml │ │ ├── vit_deit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py │ │ ├── vit_deit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py │ │ ├── vit_deit-b16_upernet_8xb2-160k_ade20k-512x512.py │ │ ├── vit_deit-b16_upernet_8xb2-80k_ade20k-512x512.py │ │ ├── vit_deit-s16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py │ │ ├── vit_deit-s16_mln_upernet_8xb2-160k_ade20k-512x512.py │ │ ├── vit_deit-s16_upernet_8xb2-160k_ade20k-512x512.py │ │ ├── vit_deit-s16_upernet_8xb2-80k_ade20k-512x512.py │ │ ├── vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py │ │ ├── vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py │ │ └── vit_vit-b16_mln_upernet_8xb2-80k_ade20k-512x512.py │ ├── vssm │ │ ├── upernet_convnext_4xb4-160k_ade20k-640x640_small.py │ │ ├── upernet_convnext_4xb4-160k_ade20k-896x896_small.py │ │ ├── upernet_internimage_g_896_160k_ade20k.py │ │ ├── upernet_swin_4xb4-160k_ade20k-640x640_small.py │ │ ├── upernet_swin_4xb4-160k_ade20k-896x896_small.py │ │ ├── upernet_vssm_4xb4-160k_ade20k-512x512_base.py │ │ ├── upernet_vssm_4xb4-160k_ade20k-512x512_small.py │ │ ├── upernet_vssm_4xb4-160k_ade20k-512x512_tiny.py │ │ ├── upernet_vssm_4xb4-160k_ade20k-640x640_small.py │ │ └── upernet_vssm_4xb4-160k_ade20k-896x896_small.py │ └── vssm1 │ │ ├── upernet_vssm_4xb4-160k_ade20k-512x512_base.py │ │ ├── upernet_vssm_4xb4-160k_ade20k-512x512_small.py │ │ ├── upernet_vssm_4xb4-160k_ade20k-512x512_tiny.py │ │ ├── upernet_vssm_4xb4-160k_ade20k-512x512_tiny1.py │ │ ├── upernet_vssm_4xb4-160k_ade20k-640x640_small.py │ │ └── upernet_vssm_4xb4-160k_ade20k-896x896_small.py ├── model.py ├── readme.md └── tools │ ├── analysis_tools │ ├── analyze_logs.py │ ├── benchmark.py │ ├── browse_dataset.py │ ├── confusion_matrix.py │ ├── get_flops.py │ └── visualization_cam.py │ ├── dataset_converters │ ├── chase_db1.py │ ├── cityscapes.py │ ├── coco_stuff10k.py │ ├── coco_stuff164k.py │ ├── drive.py │ ├── hrf.py │ ├── isaid.py │ ├── levircd.py │ ├── loveda.py │ ├── nyu.py │ ├── pascal_context.py │ ├── potsdam.py │ ├── refuge.py │ ├── stare.py │ ├── synapse.py │ ├── vaihingen.py │ └── voc_aug.py │ ├── deployment │ └── pytorch2torchscript.py │ ├── dist_test.sh │ ├── dist_train.sh │ ├── misc │ ├── browse_dataset.py │ ├── print_config.py │ └── publish_model.py │ ├── model_converters │ ├── beit2mmseg.py │ ├── clip2mmseg.py │ ├── mit2mmseg.py │ ├── san2mmseg.py │ ├── stdc2mmseg.py │ ├── swin2mmseg.py │ ├── twins2mmseg.py │ ├── vit2mmseg.py │ └── vitjax2mmseg.py │ ├── slurm_test.sh │ ├── slurm_train.sh │ ├── test.py │ ├── torchserve │ ├── mmseg2torchserve.py │ ├── mmseg_handler.py │ └── test_torchserve.py │ └── train.py └── vmamba.py /analyze/convnexts4nd/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MzeroMiko/VMamba/2ed52ead062a51a64521ed3871d52914bf532876/analyze/convnexts4nd/__init__.py -------------------------------------------------------------------------------- /analyze/convnexts4nd/extensions/kernels/README.md: -------------------------------------------------------------------------------- 1 | Install the Cauchy and Vandermonde CUDA kernels: 2 | ``` 3 | python setup.py install 4 | ``` 5 | 6 | (Optional) Test the extensions 7 | ``` 8 | pytest -q -s test_cauchy.py 9 | pytest -q -s test_vandermonde.py 10 | ``` 11 | -------------------------------------------------------------------------------- /analyze/convnexts4nd/readme.md: -------------------------------------------------------------------------------- 1 | this is a fork of [s4nd](https://github.com/state-spaces/s4) 2 | 3 | ```bash 4 | conda create -n s4 --clone vmamba 5 | pip install pytorch_lightning timm==0.5.4 hydra-core 6 | cd extensions/kernels/ && python setup.py install 7 | ``` 8 | 9 | change convnexts4nd/src/models/sequence/modules/s4nd.py#233: 10 | "int(l_i if l_k is None else min(l_i, round(l_k / rate))) for l_i, l_k in zip(L_input, self.l_max)" 11 | 12 | -------------------------------------------------------------------------------- /analyze/convnexts4nd/src/dataloaders/__init__.py: -------------------------------------------------------------------------------- 1 | from . import audio, basic, et, lm, lra, synthetic, ts, vision 2 | from .base import SequenceDataset 3 | -------------------------------------------------------------------------------- /analyze/convnexts4nd/src/models/baselines/nonaka/README.md: -------------------------------------------------------------------------------- 1 | 2 | All code adapted from codebase: https://github.com/seitalab/dnn_ecg_comparison 3 | for the paper 4 | ``` 5 | Nonaka, Seita. 6 | "In-depth Benchmarking of Deep Neural Network Architectures for ECG Diagnosis" 7 | ``` 8 | 9 | -------------------------------------------------------------------------------- /analyze/convnexts4nd/src/models/nn/__init__.py: -------------------------------------------------------------------------------- 1 | from .linear import LinearActivation, TransposedLinear 2 | from .activation import Activation 3 | from .normalization import Normalization 4 | from .dropout import DropoutNd, StochasticDepth 5 | -------------------------------------------------------------------------------- /analyze/convnexts4nd/src/models/nn/exprnn/README.md: -------------------------------------------------------------------------------- 1 | Original code from https://github.com/Lezcano/expRNN 2 | 3 | This was extracted around early 2020 and may not be the most recent version, but is compatible with this codebase. 4 | -------------------------------------------------------------------------------- /analyze/convnexts4nd/src/models/s4/README.md: -------------------------------------------------------------------------------- 1 | The standalone S4 implementation used to live here, but has been moved to [models/s4](/models/s4). 2 | -------------------------------------------------------------------------------- /analyze/convnexts4nd/src/models/sequence/__init__.py: -------------------------------------------------------------------------------- 1 | from .base import SequenceModule, TransposedModule 2 | -------------------------------------------------------------------------------- /analyze/convnexts4nd/src/models/sequence/kernels/__init__.py: -------------------------------------------------------------------------------- 1 | from .kernel import ConvKernel, EMAKernel 2 | from .ssm import SSMKernelDense, SSMKernelReal, SSMKernelDiag, SSMKernelDPLR 3 | 4 | registry = { 5 | 'conv': ConvKernel, 6 | 'ema': EMAKernel, 7 | 'dense': SSMKernelDense, 8 | 'slow': SSMKernelDense, 9 | 'real': SSMKernelReal, 10 | 's4d': SSMKernelDiag, 11 | 'diag': SSMKernelDiag, 12 | 's4': SSMKernelDPLR, 13 | 'nplr': SSMKernelDPLR, 14 | 'dplr': SSMKernelDPLR, 15 | } 16 | -------------------------------------------------------------------------------- /analyze/convnexts4nd/src/models/sequence/rnns/__init__.py: -------------------------------------------------------------------------------- 1 | # Expose the cell registry and load all possible cells 2 | from .cells.basic import CellBase 3 | from .cells import basic 4 | from .cells import hippo 5 | from .cells import timestamp 6 | from . import sru 7 | -------------------------------------------------------------------------------- /analyze/convnexts4nd/src/models/sequence/rnns/cells/__init__.py: -------------------------------------------------------------------------------- 1 | from .basic import CellBase 2 | -------------------------------------------------------------------------------- /analyze/convnexts4nd/src/utils/__init__.py: -------------------------------------------------------------------------------- 1 | from .config import is_list, is_dict, to_list, to_dict, get_class, instantiate 2 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/convmixer/convmixer-1024-20.py: -------------------------------------------------------------------------------- 1 | # Model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='ConvMixer', arch='1024/20'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1024, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | )) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/convmixer/convmixer-1536-20.py: -------------------------------------------------------------------------------- 1 | # Model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='ConvMixer', arch='1536/20'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1536, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | )) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/convmixer/convmixer-768-32.py: -------------------------------------------------------------------------------- 1 | # Model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='ConvMixer', arch='768/32', act_cfg=dict(type='ReLU')), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=768, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | )) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/convnext/__pycache__/convnext-tiny.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MzeroMiko/VMamba/2ed52ead062a51a64521ed3871d52914bf532876/analyze/mmpretrain_configs/configs/_base_/models/convnext/__pycache__/convnext-tiny.cpython-310.pyc -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/densenet/densenet121.py: -------------------------------------------------------------------------------- 1 | # Model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='DenseNet', arch='121'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1024, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | )) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/densenet/densenet161.py: -------------------------------------------------------------------------------- 1 | # Model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='DenseNet', arch='161'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=2208, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | )) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/densenet/densenet169.py: -------------------------------------------------------------------------------- 1 | # Model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='DenseNet', arch='169'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1664, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | )) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/densenet/densenet201.py: -------------------------------------------------------------------------------- 1 | # Model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='DenseNet', arch='201'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1920, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | )) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_b0.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNet', arch='b0'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1280, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_b1.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNet', arch='b1'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1280, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_b2.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNet', arch='b2'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1408, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_b3.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNet', arch='b3'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1536, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_b4.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNet', arch='b4'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1792, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_b5.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNet', arch='b5'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=2048, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_b6.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNet', arch='b6'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=2304, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_b7.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNet', arch='b7'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=2560, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_b8.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNet', arch='b8'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=2816, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_l2.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNet', arch='l2'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=5504, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_v2/efficientnetv2_b0.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNetV2', arch='b0'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1280, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_v2/efficientnetv2_b1.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNetV2', arch='b1'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1280, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_v2/efficientnetv2_b2.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNetV2', arch='b2'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1408, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_v2/efficientnetv2_b3.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNetV2', arch='b3'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1536, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_v2/efficientnetv2_l.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNetV2', arch='l'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1280, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_v2/efficientnetv2_m.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNetV2', arch='m'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1280, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_v2/efficientnetv2_s.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNetV2', arch='s'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1280, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/efficientnet_v2/efficientnetv2_xl.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='EfficientNetV2', arch='xl'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1280, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/inception_v3.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='InceptionV3', num_classes=1000, aux_logits=False), 5 | neck=None, 6 | head=dict( 7 | type='ClsHead', 8 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 9 | topk=(1, 5)), 10 | ) 11 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/mobilenet_v2_1x.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='MobileNetV2', widen_factor=1.0), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1280, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/mobilevit/mobilevit_s.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='MobileViT', arch='small'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=640, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/mobilevit/mobilevit_xs.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='MobileViT', arch='x_small'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=384, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/mobilevit/mobilevit_xxs.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='MobileViT', arch='xx_small'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=320, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/regnet/regnetx_1.6gf.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='RegNet', arch='regnetx_1.6gf'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=912, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/regnet/regnetx_12gf.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='RegNet', arch='regnetx_12gf'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=2240, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/regnet/regnetx_3.2gf.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='RegNet', arch='regnetx_3.2gf'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1008, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/regnet/regnetx_4.0gf.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='RegNet', arch='regnetx_4.0gf'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1360, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/regnet/regnetx_400mf.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='RegNet', arch='regnetx_400mf'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=384, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/regnet/regnetx_6.4gf.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='RegNet', arch='regnetx_6.4gf'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1624, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/regnet/regnetx_8.0gf.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='RegNet', arch='regnetx_8.0gf'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1920, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/regnet/regnetx_800mf.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='RegNet', arch='regnetx_800mf'), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=672, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/replknet-31L_in1k.py: -------------------------------------------------------------------------------- 1 | model = dict( 2 | type='ImageClassifier', 3 | backbone=dict( 4 | type='RepLKNet', 5 | arch='31L', 6 | out_indices=(3, ), 7 | ), 8 | neck=dict(type='GlobalAveragePooling'), 9 | head=dict( 10 | type='LinearClsHead', 11 | num_classes=1000, 12 | in_channels=1536, 13 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 14 | topk=(1, 5), 15 | )) 16 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/replknet-XL_in1k.py: -------------------------------------------------------------------------------- 1 | model = dict( 2 | type='ImageClassifier', 3 | backbone=dict( 4 | type='RepLKNet', 5 | arch='XL', 6 | out_indices=(3, ), 7 | ), 8 | neck=dict(type='GlobalAveragePooling'), 9 | head=dict( 10 | type='LinearClsHead', 11 | num_classes=1000, 12 | in_channels=2048, 13 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 14 | topk=(1, 5), 15 | )) 16 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/repvgg-A0_in1k.py: -------------------------------------------------------------------------------- 1 | model = dict( 2 | type='ImageClassifier', 3 | backbone=dict( 4 | type='RepVGG', 5 | arch='A0', 6 | out_indices=(3, ), 7 | ), 8 | neck=dict(type='GlobalAveragePooling'), 9 | head=dict( 10 | type='LinearClsHead', 11 | num_classes=1000, 12 | in_channels=1280, 13 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 14 | topk=(1, 5), 15 | )) 16 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/shufflenet_v1_1x.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='ShuffleNetV1', groups=3), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=960, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/shufflenet_v2_1x.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='ShuffleNetV2', widen_factor=1.0), 5 | neck=dict(type='GlobalAveragePooling'), 6 | head=dict( 7 | type='LinearClsHead', 8 | num_classes=1000, 9 | in_channels=1024, 10 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 11 | topk=(1, 5), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/swin_transformer/__pycache__/tiny_224.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MzeroMiko/VMamba/2ed52ead062a51a64521ed3871d52914bf532876/analyze/mmpretrain_configs/configs/_base_/models/swin_transformer/__pycache__/tiny_224.cpython-310.pyc -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/swin_transformer/large_224.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | # Only for evaluation 3 | model = dict( 4 | type='ImageClassifier', 5 | backbone=dict(type='SwinTransformer', arch='large', img_size=224), 6 | neck=dict(type='GlobalAveragePooling'), 7 | head=dict( 8 | type='LinearClsHead', 9 | num_classes=1000, 10 | in_channels=1536, 11 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 12 | topk=(1, 5))) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/vgg11.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='VGG', depth=11, num_classes=1000), 5 | neck=None, 6 | head=dict( 7 | type='ClsHead', 8 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 9 | topk=(1, 5), 10 | )) 11 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/vgg11bn.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict( 5 | type='VGG', depth=11, norm_cfg=dict(type='BN'), num_classes=1000), 6 | neck=None, 7 | head=dict( 8 | type='ClsHead', 9 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 10 | topk=(1, 5), 11 | )) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/vgg13.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='VGG', depth=13, num_classes=1000), 5 | neck=None, 6 | head=dict( 7 | type='ClsHead', 8 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 9 | topk=(1, 5), 10 | )) 11 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/vgg13bn.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict( 5 | type='VGG', depth=13, norm_cfg=dict(type='BN'), num_classes=1000), 6 | neck=None, 7 | head=dict( 8 | type='ClsHead', 9 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 10 | topk=(1, 5), 11 | )) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/vgg16.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='VGG', depth=16, num_classes=1000), 5 | neck=None, 6 | head=dict( 7 | type='ClsHead', 8 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 9 | topk=(1, 5), 10 | )) 11 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/vgg16bn.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict( 5 | type='VGG', depth=16, norm_cfg=dict(type='BN'), num_classes=1000), 6 | neck=None, 7 | head=dict( 8 | type='ClsHead', 9 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 10 | topk=(1, 5), 11 | )) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/vgg19.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict(type='VGG', depth=19, num_classes=1000), 5 | neck=None, 6 | head=dict( 7 | type='ClsHead', 8 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 9 | topk=(1, 5), 10 | )) 11 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/models/vgg19bn.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='ImageClassifier', 4 | backbone=dict( 5 | type='VGG', depth=19, norm_cfg=dict(type='BN'), num_classes=1000), 6 | neck=None, 7 | head=dict( 8 | type='ClsHead', 9 | loss=dict(type='CrossEntropyLoss', loss_weight=1.0), 10 | topk=(1, 5), 11 | )) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/schedules/imagenet_lars_coslr_90e.py: -------------------------------------------------------------------------------- 1 | # optimizer wrapper 2 | optim_wrapper = dict( 3 | type='OptimWrapper', 4 | optimizer=dict(type='LARS', lr=1.6, momentum=0.9, weight_decay=0.)) 5 | 6 | # learning rate scheduler 7 | param_scheduler = [ 8 | dict(type='CosineAnnealingLR', T_max=90, by_epoch=True, begin=0, end=90) 9 | ] 10 | 11 | # runtime settings 12 | train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=90) 13 | val_cfg = dict() 14 | test_cfg = dict() 15 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/schedules/imagenet_sgd_coslr_100e.py: -------------------------------------------------------------------------------- 1 | # optimizer wrapper 2 | optim_wrapper = dict( 3 | type='OptimWrapper', 4 | optimizer=dict(type='SGD', lr=0.3, momentum=0.9, weight_decay=1e-6)) 5 | 6 | # learning rate scheduler 7 | param_scheduler = [ 8 | dict(type='CosineAnnealingLR', T_max=100, by_epoch=True, begin=0, end=100) 9 | ] 10 | 11 | # runtime settings 12 | train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=100) 13 | val_cfg = dict() 14 | test_cfg = dict() 15 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/schedules/imagenet_sgd_coslr_200e.py: -------------------------------------------------------------------------------- 1 | # optimizer wrapper 2 | optim_wrapper = dict( 3 | type='OptimWrapper', 4 | optimizer=dict(type='SGD', lr=0.03, weight_decay=1e-4, momentum=0.9)) 5 | 6 | # learning rate scheduler 7 | param_scheduler = [ 8 | dict(type='CosineAnnealingLR', T_max=200, by_epoch=True, begin=0, end=200) 9 | ] 10 | 11 | # runtime settings 12 | train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=200) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/_base_/schedules/imagenet_sgd_steplr_100e.py: -------------------------------------------------------------------------------- 1 | # optimizer wrapper 2 | optim_wrapper = dict( 3 | type='OptimWrapper', 4 | optimizer=dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=1e-4)) 5 | 6 | # learning rate scheduler 7 | param_scheduler = [ 8 | dict(type='MultiStepLR', by_epoch=True, milestones=[60, 80], gamma=0.1) 9 | ] 10 | 11 | # runtime settings 12 | train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=100) 13 | val_cfg = dict() 14 | test_cfg = dict() 15 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/conformer/conformer-base-p16_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/conformer/base-p16.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_conformer.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | train_dataloader = dict(batch_size=128) 9 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/conformer/conformer-small-p16_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/conformer/small-p16.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_conformer.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | train_dataloader = dict(batch_size=128) 9 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/conformer/conformer-small-p32_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/conformer/small-p32.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_conformer.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | train_dataloader = dict(batch_size=128) 9 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/conformer/conformer-tiny-p16_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/conformer/tiny-p16.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_conformer.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | train_dataloader = dict(batch_size=128) 9 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/davit/davit-base_4xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/davit/davit-base.py', 3 | '../_base_/datasets/imagenet_bs256_davit_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # data settings 9 | train_dataloader = dict(batch_size=256) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/davit/davit-small_4xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/davit/davit-small.py', 3 | '../_base_/datasets/imagenet_bs256_davit_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # data settings 9 | train_dataloader = dict(batch_size=256) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/davit/davit-tiny_4xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/davit/davit-tiny.py', 3 | '../_base_/datasets/imagenet_bs256_davit_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # data settings 9 | train_dataloader = dict(batch_size=256) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/efficientformer/efficientformer-l1_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/efficientformer-l1.py', 3 | '../_base_/datasets/imagenet_bs128_poolformer_small_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/efficientformer/efficientformer-l3_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = './efficientformer-l1_8xb128_in1k.py' 2 | 3 | model = dict(backbone=dict(arch='l3'), head=dict(in_channels=512)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/efficientformer/efficientformer-l7_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = './efficientformer-l1_8xb128_in1k.py' 2 | 3 | model = dict(backbone=dict(arch='l7'), head=dict(in_channels=768)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/efficientnet_v2/efficientnetv2-l_8xb32_in21k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./efficientnetv2-s_8xb32_in21k.py'] 2 | 3 | # model setting 4 | model = dict(backbone=dict(arch='l'), ) 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/efficientnet_v2/efficientnetv2-m_8xb32_in21k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./efficientnetv2-s_8xb32_in21k.py'] 2 | 3 | # model setting 4 | model = dict(backbone=dict(arch='m'), ) 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/efficientnet_v2/efficientnetv2-xl_8xb32_in21k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./efficientnetv2-s_8xb32_in21k.py'] 2 | 3 | # model setting 4 | model = dict(backbone=dict(arch='xl'), ) 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/eva/eva-g-p14_8xb16_in1k-336px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/eva/eva-g.py', 3 | '../_base_/datasets/imagenet_bs16_eva_336.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # model settings 9 | model = dict(backbone=dict(img_size=336)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/eva/eva-g-p14_8xb16_in1k-560px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/eva/eva-g.py', 3 | '../_base_/datasets/imagenet_bs16_eva_560.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # model settings 9 | model = dict(backbone=dict(img_size=560)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/eva/eva-l-p14_8xb16_in1k-196px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/eva/eva-l.py', 3 | '../_base_/datasets/imagenet_bs16_eva_196.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # model settings 9 | model = dict(backbone=dict(img_size=196)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/eva/eva-l-p14_8xb16_in1k-336px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/eva/eva-l.py', 3 | '../_base_/datasets/imagenet_bs16_eva_336.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # model settings 9 | model = dict(backbone=dict(img_size=336)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hivit/hivit-base-p16_16xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hivit/base_224.py', 3 | '../_base_/datasets/imagenet_bs64_hivit_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_hivit.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # schedule settings 9 | optim_wrapper = dict(clip_grad=dict(max_norm=5.0)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hivit/hivit-small-p16_16xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hivit/small_224.py', 3 | '../_base_/datasets/imagenet_bs64_hivit_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_hivit.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # schedule settings 9 | optim_wrapper = dict(clip_grad=dict(max_norm=5.0)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hivit/hivit-tiny-p16_16xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hivit/tiny_224.py', 3 | '../_base_/datasets/imagenet_bs64_hivit_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_hivit.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # schedule settings 9 | optim_wrapper = dict(clip_grad=dict(max_norm=5.0)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hornet/hornet-base-gf_8xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hornet/hornet-base-gf.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | data = dict(samples_per_gpu=64) 9 | 10 | optim_wrapper = dict(optimizer=dict(lr=4e-3), clip_grad=dict(max_norm=1.0)) 11 | 12 | custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')] 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hornet/hornet-base_8xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hornet/hornet-base.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | data = dict(samples_per_gpu=64) 9 | 10 | optim_wrapper = dict(optimizer=dict(lr=4e-3), clip_grad=dict(max_norm=5.0)) 11 | 12 | custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')] 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hornet/hornet-small-gf_8xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hornet/hornet-small-gf.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | data = dict(samples_per_gpu=64) 9 | 10 | optim_wrapper = dict(optimizer=dict(lr=4e-3), clip_grad=dict(max_norm=1.0)) 11 | 12 | custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')] 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hornet/hornet-small_8xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hornet/hornet-small.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | data = dict(samples_per_gpu=64) 9 | 10 | optim_wrapper = dict(optimizer=dict(lr=4e-3), clip_grad=dict(max_norm=5.0)) 11 | 12 | custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')] 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hornet/hornet-tiny-gf_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hornet/hornet-tiny-gf.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | data = dict(samples_per_gpu=128) 9 | 10 | optim_wrapper = dict(optimizer=dict(lr=4e-3), clip_grad=dict(max_norm=1.0)) 11 | 12 | custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')] 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hornet/hornet-tiny_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hornet/hornet-tiny.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | data = dict(samples_per_gpu=128) 9 | 10 | optim_wrapper = dict(optimizer=dict(lr=4e-3), clip_grad=dict(max_norm=100.0)) 11 | 12 | custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')] 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hrnet/hrnet-w18_4xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hrnet/hrnet-w18.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256_coslr.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # NOTE: `auto_scale_lr` is for automatically scaling LR 9 | # based on the actual training batch size. 10 | # base_batch_size = (4 GPUs) x (32 samples per GPU) 11 | auto_scale_lr = dict(base_batch_size=128) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hrnet/hrnet-w30_4xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hrnet/hrnet-w30.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256_coslr.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # NOTE: `auto_scale_lr` is for automatically scaling LR 9 | # based on the actual training batch size. 10 | # base_batch_size = (4 GPUs) x (32 samples per GPU) 11 | auto_scale_lr = dict(base_batch_size=128) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hrnet/hrnet-w32_4xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hrnet/hrnet-w32.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256_coslr.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # NOTE: `auto_scale_lr` is for automatically scaling LR 9 | # based on the actual training batch size. 10 | # base_batch_size = (4 GPUs) x (32 samples per GPU) 11 | auto_scale_lr = dict(base_batch_size=128) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hrnet/hrnet-w40_4xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hrnet/hrnet-w40.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256_coslr.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # NOTE: `auto_scale_lr` is for automatically scaling LR 9 | # based on the actual training batch size. 10 | # base_batch_size = (4 GPUs) x (32 samples per GPU) 11 | auto_scale_lr = dict(base_batch_size=128) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hrnet/hrnet-w44_4xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hrnet/hrnet-w44.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256_coslr.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # NOTE: `auto_scale_lr` is for automatically scaling LR 9 | # based on the actual training batch size. 10 | # base_batch_size = (4 GPUs) x (32 samples per GPU) 11 | auto_scale_lr = dict(base_batch_size=128) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hrnet/hrnet-w48_4xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hrnet/hrnet-w48.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256_coslr.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # NOTE: `auto_scale_lr` is for automatically scaling LR 9 | # based on the actual training batch size. 10 | # base_batch_size = (4 GPUs) x (32 samples per GPU) 11 | auto_scale_lr = dict(base_batch_size=128) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/hrnet/hrnet-w64_4xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/hrnet/hrnet-w64.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256_coslr.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # NOTE: `auto_scale_lr` is for automatically scaling LR 9 | # based on the actual training batch size. 10 | # base_batch_size = (4 GPUs) x (32 samples per GPU) 11 | auto_scale_lr = dict(base_batch_size=128) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/levit/deploy/levit-128_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = '../levit-128_8xb256_in1k.py' 2 | 3 | model = dict(backbone=dict(deploy=True), head=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/levit/deploy/levit-128s_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = '../levit-128s_8xb256_in1k.py' 2 | 3 | model = dict(backbone=dict(deploy=True), head=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/levit/deploy/levit-192_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = '../levit-192_8xb256_in1k.py' 2 | 3 | model = dict(backbone=dict(deploy=True), head=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/levit/deploy/levit-256_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = '../levit-256_8xb256_in1k.py' 2 | 3 | model = dict(backbone=dict(deploy=True), head=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/levit/deploy/levit-384_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = '../levit-384_8xb256_in1k.py' 2 | 3 | model = dict(backbone=dict(deploy=True), head=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/levit/levit-128_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/levit-256-p16.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs2048_adamw_levit.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | # model settings 9 | model = dict(backbone=dict(arch='128'), head=dict(in_channels=384)) 10 | 11 | # dataset settings 12 | train_dataloader = dict(batch_size=256) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/levit/levit-128s_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/levit-256-p16.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs2048_adamw_levit.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | # model settings 9 | model = dict(backbone=dict(arch='128s'), head=dict(in_channels=384)) 10 | 11 | # dataset settings 12 | train_dataloader = dict(batch_size=256) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/levit/levit-192_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/levit-256-p16.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs2048_adamw_levit.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | # model settings 9 | model = dict(backbone=dict(arch='192'), head=dict(in_channels=384)) 10 | 11 | # dataset settings 12 | train_dataloader = dict(batch_size=256) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/levit/levit-256_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/levit-256-p16.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs2048_adamw_levit.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | # dataset settings 9 | train_dataloader = dict(batch_size=256) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/levit/levit-384_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/levit-256-p16.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs2048_adamw_levit.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | # model settings 9 | model = dict( 10 | backbone=dict(arch='384', drop_path_rate=0.1), 11 | head=dict(in_channels=768), 12 | ) 13 | 14 | # dataset settings 15 | train_dataloader = dict(batch_size=256) 16 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/mae/benchmarks/vit-huge-p14_8xb128-fsdp-coslr-50e_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./vit-huge-p14_8xb128-coslr-50e_in1k.py'] 2 | 3 | strategy = dict( 4 | type='FSDPStrategy', 5 | model_wrapper=dict( 6 | auto_wrap_policy=dict( 7 | type='torch.distributed.fsdp.wrap.size_based_auto_wrap_policy', 8 | min_num_params=1e7))) 9 | 10 | optim_wrapper = dict(type='AmpOptimWrapper') 11 | 12 | # runner which supports strategies 13 | runner_type = 'FlexibleRunner' 14 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/mixmim/benchmarks/mixmim-base_8xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../../_base_/models/mixmim/mixmim_base.py', 3 | '../../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../../_base_/schedules/imagenet_bs256.py', 5 | '../../_base_/default_runtime.py' 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/mlp_mixer/mlp-mixer-base-p16_64xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/mlp_mixer_base_patch16.py', 3 | '../_base_/datasets/imagenet_bs64_mixer_224.py', 4 | '../_base_/schedules/imagenet_bs4096_AdamW.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | optim_wrapper = dict(clip_grad=dict(max_norm=1.0)) 9 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/mlp_mixer/mlp-mixer-large-p16_64xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/mlp_mixer_large_patch16.py', 3 | '../_base_/datasets/imagenet_bs64_mixer_224.py', 4 | '../_base_/schedules/imagenet_bs4096_AdamW.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | optim_wrapper = dict(clip_grad=dict(max_norm=1.0)) 9 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/mobilenet_v2/mobilenet-v2_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/mobilenet_v2_1x.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256_epochstep.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/mobileone/deploy/mobileone-s0_deploy_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['../mobileone-s0_8xb32_in1k.py'] 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/mobileone/deploy/mobileone-s1_deploy_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['../mobileone-s1_8xb32_in1k.py'] 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/mobileone/deploy/mobileone-s2_deploy_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['../mobileone-s2_8xb32_in1k.py'] 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/mobileone/deploy/mobileone-s3_deploy_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['../mobileone-s3_8xb32_in1k.py'] 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/mobileone/deploy/mobileone-s4_deploy_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['../mobileone-s4_8xb32_in1k.py'] 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/regnet/regnetx-1.6gf_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./regnetx-400mf_8xb128_in1k.py'] 2 | 3 | # model settings 4 | model = dict( 5 | backbone=dict(type='RegNet', arch='regnetx_1.6gf'), 6 | head=dict(in_channels=912, )) 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/regnet/regnetx-800mf_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./regnetx-400mf_8xb128_in1k.py'] 2 | 3 | # model settings 4 | model = dict( 5 | backbone=dict(type='RegNet', arch='regnetx_800mf'), 6 | head=dict(in_channels=672, )) 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/replknet/deploy/replknet-31B-deploy_32xb64_in1k-384px.py: -------------------------------------------------------------------------------- 1 | _base_ = '../replknet-31B_32xb64_in1k-384px.py' 2 | 3 | model = dict(backbone=dict(small_kernel_merged=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/replknet/deploy/replknet-31B-deploy_32xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = '../replknet-31B_32xb64_in1k.py' 2 | 3 | model = dict(backbone=dict(small_kernel_merged=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/replknet/deploy/replknet-31L-deploy_32xb64_in1k-384px.py: -------------------------------------------------------------------------------- 1 | _base_ = '../replknet-31L_32xb64_in1k-384px.py' 2 | 3 | model = dict(backbone=dict(small_kernel_merged=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/replknet/deploy/replknet-XL-deploy_32xb64_in1k-320px.py: -------------------------------------------------------------------------------- 1 | _base_ = '../replknet-XL_32xb64_in1k-320px.py' 2 | 3 | model = dict(backbone=dict(small_kernel_merged=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/replknet/replknet-31B_32xb64_in1k-384px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/replknet-31B_in1k.py', 3 | '../_base_/datasets/imagenet_bs16_pil_bicubic_384.py', 4 | '../_base_/schedules/imagenet_bs256_coslr.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # schedule settings 9 | param_scheduler = dict( 10 | type='CosineAnnealingLR', T_max=300, by_epoch=True, begin=0, end=300) 11 | 12 | train_cfg = dict(by_epoch=True, max_epochs=300) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/replknet/replknet-31B_32xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/replknet-31B_in1k.py', 3 | '../_base_/datasets/imagenet_bs32_pil_bicubic.py', 4 | '../_base_/schedules/imagenet_bs256_coslr.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # schedule settings 9 | param_scheduler = dict( 10 | type='CosineAnnealingLR', T_max=300, by_epoch=True, begin=0, end=300) 11 | 12 | train_cfg = dict(by_epoch=True, max_epochs=300) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/replknet/replknet-31L_32xb64_in1k-384px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/replknet-31L_in1k.py', 3 | '../_base_/datasets/imagenet_bs16_pil_bicubic_384.py', 4 | '../_base_/schedules/imagenet_bs256_coslr.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # schedule settings 9 | param_scheduler = dict( 10 | type='CosineAnnealingLR', T_max=300, by_epoch=True, begin=0, end=300) 11 | 12 | train_cfg = dict(by_epoch=True, max_epochs=300) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/replknet/replknet-XL_32xb64_in1k-320px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/replknet-XL_in1k.py', 3 | '../_base_/datasets/imagenet_bs8_pil_bicubic_320.py', 4 | '../_base_/schedules/imagenet_bs256_coslr.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # schedule settings 9 | param_scheduler = dict( 10 | type='CosineAnnealingLR', T_max=300, by_epoch=True, begin=0, end=300) 11 | 12 | train_cfg = dict(by_epoch=True, max_epochs=300) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/repmlp/repmlp-base_delopy_8xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./repmlp-base_8xb64_in1k.py'] 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/repmlp/repmlp-base_deploy_8xb64_in1k-256px.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./repmlp-base_8xb64_in1k-256px.py'] 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/repvgg/repvgg-A0_deploy_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = './repvgg-A0_8xb32_in1k.py' 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/repvgg/repvgg-A1_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = './repvgg-A0_8xb32_in1k.py' 2 | 3 | model = dict(backbone=dict(arch='A1')) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/repvgg/repvgg-A2_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = './repvgg-A0_8xb32_in1k.py' 2 | 3 | model = dict(backbone=dict(arch='A2'), head=dict(in_channels=1408)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/repvgg/repvgg-B0_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = './repvgg-A0_8xb32_in1k.py' 2 | 3 | model = dict(backbone=dict(arch='B0'), head=dict(in_channels=1280)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/repvgg/repvgg-B1_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = './repvgg-A0_8xb32_in1k.py' 2 | 3 | model = dict(backbone=dict(arch='B1'), head=dict(in_channels=2048)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/repvgg/repvgg-B1g2_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = './repvgg-A0_8xb32_in1k.py' 2 | 3 | model = dict(backbone=dict(arch='B1g2'), head=dict(in_channels=2048)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/repvgg/repvgg-B1g4_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = './repvgg-A0_8xb32_in1k.py' 2 | 3 | model = dict(backbone=dict(arch='B1g4'), head=dict(in_channels=2048)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/repvgg/repvgg-B2_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = './repvgg-A0_8xb32_in1k.py' 2 | 3 | model = dict(backbone=dict(arch='B2'), head=dict(in_channels=2560)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/repvgg/repvgg-B2g4_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = './repvgg-B3_8xb32_in1k.py' 2 | 3 | model = dict(backbone=dict(arch='B2g4'), head=dict(in_channels=2560)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/repvgg/repvgg-B3g4_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = './repvgg-B3_8xb32_in1k.py' 2 | 3 | model = dict(backbone=dict(arch='B3g4')) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/res2net/res2net101-w26-s4_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/res2net101-w26-s4.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/res2net/res2net50-w14-s8_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/res2net50-w14-s8.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/res2net/res2net50-w26-s8_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/res2net50-w26-s8.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet101_8xb16_cifar10.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet101_cifar.py', 3 | '../_base_/datasets/cifar10_bs16.py', 4 | '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet101_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet101.py', '../_base_/datasets/imagenet_bs32.py', 3 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 4 | ] 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet152_8xb16_cifar10.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet152_cifar.py', 3 | '../_base_/datasets/cifar10_bs16.py', 4 | '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet152_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet152.py', '../_base_/datasets/imagenet_bs32.py', 3 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 4 | ] 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet18_8xb16_cifar10.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet18_cifar.py', '../_base_/datasets/cifar10_bs16.py', 3 | '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py' 4 | ] 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet18_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet18.py', '../_base_/datasets/imagenet_bs32.py', 3 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 4 | ] 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet34_8xb16_cifar10.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet34_cifar.py', '../_base_/datasets/cifar10_bs16.py', 3 | '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py' 4 | ] 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet34_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet34.py', '../_base_/datasets/imagenet_bs32.py', 3 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 4 | ] 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet50_32xb64-warmup-coslr_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet50.py', '../_base_/datasets/imagenet_bs64.py', 3 | '../_base_/schedules/imagenet_bs2048_coslr.py', 4 | '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet50_32xb64-warmup-lbs_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./resnet50_32xb64-warmup_in1k.py'] 2 | model = dict( 3 | head=dict( 4 | type='LinearClsHead', 5 | num_classes=1000, 6 | in_channels=2048, 7 | loss=dict( 8 | type='LabelSmoothLoss', 9 | loss_weight=1.0, 10 | label_smooth_val=0.1, 11 | num_classes=1000), 12 | )) 13 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet50_32xb64-warmup_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet50.py', '../_base_/datasets/imagenet_bs64.py', 3 | '../_base_/schedules/imagenet_bs2048.py', '../_base_/default_runtime.py' 4 | ] 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet50_8xb128_coslr-90e_in21k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet50.py', '../_base_/datasets/imagenet21k_bs128.py', 3 | '../_base_/schedules/imagenet_bs1024_coslr.py', 4 | '../_base_/default_runtime.py' 5 | ] 6 | 7 | # model settings 8 | model = dict(head=dict(num_classes=21843)) 9 | 10 | # runtime settings 11 | train_cfg = dict(by_epoch=True, max_epochs=90) 12 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet50_8xb16-mixup_cifar10.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet50_cifar_mixup.py', 3 | '../_base_/datasets/cifar10_bs16.py', 4 | '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet50_8xb16_cifar10.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet50_cifar.py', '../_base_/datasets/cifar10_bs16.py', 3 | '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py' 4 | ] 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet50_8xb32-coslr_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet50.py', '../_base_/datasets/imagenet_bs32.py', 3 | '../_base_/schedules/imagenet_bs256_coslr.py', 4 | '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet50_8xb32-cutmix_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet50_cutmix.py', 3 | '../_base_/datasets/imagenet_bs32.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet50_8xb32-fp16-dynamic_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./resnet50_8xb32_in1k.py'] 2 | 3 | # schedule settings 4 | optim_wrapper = dict(type='AmpOptimWrapper', loss_scale='dynamic') 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet50_8xb32-fp16_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./resnet50_8xb32_in1k.py'] 2 | 3 | # schedule settings 4 | optim_wrapper = dict(type='AmpOptimWrapper', loss_scale=512.) 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet50_8xb32-lbs_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet50_label_smooth.py', 3 | '../_base_/datasets/imagenet_bs32.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet50_8xb32-mixup_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet50_mixup.py', 3 | '../_base_/datasets/imagenet_bs32.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnet50_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnet50.py', '../_base_/datasets/imagenet_bs32.py', 3 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 4 | ] 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnetv1c101_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnetv1c50.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | 7 | model = dict(backbone=dict(depth=101)) 8 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnetv1c152_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnetv1c50.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | 7 | model = dict(backbone=dict(depth=152)) 8 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnetv1c50_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnetv1c50.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnetv1d101_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnetv1d101.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnetv1d152_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnetv1d152.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnet/resnetv1d50_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnetv1d50.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnext/resnext101-32x4d_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnext101_32x4d.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnext/resnext101-32x8d_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnext101_32x8d.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnext/resnext152-32x4d_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnext152_32x4d.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/resnext/resnext50-32x4d_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/resnext50_32x4d.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/revvit/revvit-base_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/revvit/revvit-base.py', 3 | '../_base_/datasets/imagenet_bs128_revvit_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_revvit.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/revvit/revvit-small_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/revvit/revvit-small.py', 3 | '../_base_/datasets/imagenet_bs128_revvit_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_revvit.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/riformer/deploy/riformer-m36-deploy_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = '../riformer-m36_8xb128_in1k.py' 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/riformer/deploy/riformer-m36-deploy_8xb64_in1k-384px.py: -------------------------------------------------------------------------------- 1 | _base_ = '../riformer-m36_8xb64_in1k-384px.py' 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/riformer/deploy/riformer-m48-deploy_8xb64_in1k-384px.py: -------------------------------------------------------------------------------- 1 | _base_ = '../riformer-m48_8xb64_in1k-384px.py' 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/riformer/deploy/riformer-m48-deploy_8xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = '../riformer-m48_8xb64_in1k.py' 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/riformer/deploy/riformer-s12-deploy_8xb128_in1k-384px.py: -------------------------------------------------------------------------------- 1 | _base_ = '../riformer-s12_8xb128_in1k-384px.py' 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/riformer/deploy/riformer-s12-deploy_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = '../riformer-s12_8xb128_in1k.py' 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/riformer/deploy/riformer-s24-deploy_8xb128_in1k-384px.py: -------------------------------------------------------------------------------- 1 | _base_ = '../riformer-s24_8xb128_in1k-384px.py' 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/riformer/deploy/riformer-s24-deploy_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = '../riformer-s24_8xb128_in1k.py' 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/riformer/deploy/riformer-s36-deploy_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = '../riformer-s36_8xb128_in1k.py' 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/riformer/deploy/riformer-s36-deploy_8xb64_in1k-384px.py: -------------------------------------------------------------------------------- 1 | _base_ = '../riformer-s36_8xb64_in1k-384px.py' 2 | 3 | model = dict(backbone=dict(deploy=True)) 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/seresnet/seresnet101_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/seresnet101.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/seresnet/seresnet50_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/seresnet50.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256_140e.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/seresnet/seresnext101-32x4d_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/seresnext101_32x4d.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/seresnet/seresnext50-32x4d_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/seresnext50_32x4d.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/shufflenet_v1/shufflenet-v1-1x_16xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/shufflenet_v1_1x.py', 3 | '../_base_/datasets/imagenet_bs64_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs1024_linearlr_bn_nowd.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/shufflenet_v2/shufflenet-v2-1x_16xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/shufflenet_v2_1x.py', 3 | '../_base_/datasets/imagenet_bs64_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs1024_linearlr_bn_nowd.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/simmim/simmim_swin-base-w6_16xb128-amp-coslr-100e_in1k-192px.py: -------------------------------------------------------------------------------- 1 | _base_ = 'simmim_swin-base-w6_8xb256-amp-coslr-100e_in1k-192px.py' 2 | 3 | # dataset 16 GPUs x 128 4 | train_dataloader = dict(batch_size=128) 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/swin_transformer/swin-base_16xb64_in1k-384px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/swin_transformer/base_384.py', 3 | '../_base_/datasets/imagenet_bs64_swin_384.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # schedule settings 9 | optim_wrapper = dict(clip_grad=dict(max_norm=5.0)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/swin_transformer/swin-base_16xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/swin_transformer/base_224.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # schedule settings 9 | optim_wrapper = dict(clip_grad=dict(max_norm=5.0)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/swin_transformer/swin-large_16xb64_in1k-384px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/swin_transformer/large_384.py', 3 | '../_base_/datasets/imagenet_bs64_swin_384.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # schedule settings 9 | optim_wrapper = dict(clip_grad=dict(max_norm=5.0)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/swin_transformer/swin-large_16xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/swin_transformer/large_224.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # schedule settings 9 | optim_wrapper = dict(clip_grad=dict(max_norm=5.0)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/swin_transformer/swin-small_16xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/swin_transformer/small_224.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # schedule settings 9 | optim_wrapper = dict(clip_grad=dict(max_norm=5.0)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/swin_transformer/swin-tiny_16xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/swin_transformer/tiny_224.py', 3 | '../_base_/datasets/imagenet_bs64_swin_224.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | # schedule settings 9 | optim_wrapper = dict(clip_grad=dict(max_norm=5.0)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/swin_transformer_v2/swinv2-base-w16_16xb64_in1k-256px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/swin_transformer_v2/base_256.py', 3 | '../_base_/datasets/imagenet_bs64_swin_256.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | model = dict(backbone=dict(window_size=[16, 16, 16, 8])) 9 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/swin_transformer_v2/swinv2-base-w8_16xb64_in1k-256px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/swin_transformer_v2/base_256.py', 3 | '../_base_/datasets/imagenet_bs64_swin_256.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/swin_transformer_v2/swinv2-small-w16_16xb64_in1k-256px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/swin_transformer_v2/small_256.py', 3 | '../_base_/datasets/imagenet_bs64_swin_256.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | model = dict(backbone=dict(window_size=[16, 16, 16, 8])) 9 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/swin_transformer_v2/swinv2-small-w8_16xb64_in1k-256px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/swin_transformer_v2/small_256.py', 3 | '../_base_/datasets/imagenet_bs64_swin_256.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/swin_transformer_v2/swinv2-tiny-w16_16xb64_in1k-256px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/swin_transformer_v2/tiny_256.py', 3 | '../_base_/datasets/imagenet_bs64_swin_256.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | 8 | model = dict(backbone=dict(window_size=[16, 16, 16, 8])) 9 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/swin_transformer_v2/swinv2-tiny-w8_16xb64_in1k-256px.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/swin_transformer_v2/tiny_256.py', 3 | '../_base_/datasets/imagenet_bs64_swin_256.py', 4 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 5 | '../_base_/default_runtime.py' 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/tinyvit/tinyvit-11m-distill_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | './tinyvit-11m_8xb256_in1k.py', 3 | ] 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/tinyvit/tinyvit-11m_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/datasets/imagenet_bs32_pil_bicubic.py', 3 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 4 | '../_base_/default_runtime.py', 5 | '../_base_/models/tinyvit/tinyvit-11m.py', 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/tinyvit/tinyvit-21m-distill_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | './tinyvit-21m_8xb256_in1k.py', 3 | ] 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/tinyvit/tinyvit-21m_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/datasets/imagenet_bs32_pil_bicubic.py', 3 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 4 | '../_base_/default_runtime.py', 5 | '../_base_/models/tinyvit/tinyvit-21m.py', 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/tinyvit/tinyvit-5m-distill_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | './tinyvit-5m_8xb256_in1k.py', 3 | ] 4 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/tinyvit/tinyvit-5m_8xb256_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/datasets/imagenet_bs32_pil_bicubic.py', 3 | '../_base_/schedules/imagenet_bs1024_adamw_swin.py', 4 | '../_base_/default_runtime.py', 5 | '../_base_/models/tinyvit/tinyvit-5m.py', 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/twins/twins-pcpvt-large_16xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['twins-pcpvt-base_8xb128_in1k.py'] 2 | 3 | # model settings 4 | model = dict(backbone=dict(arch='large'), head=dict(in_channels=512)) 5 | 6 | # dataset settings 7 | train_dataloader = dict(batch_size=64) 8 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/twins/twins-pcpvt-small_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['twins-pcpvt-base_8xb128_in1k.py'] 2 | 3 | # model settings 4 | model = dict(backbone=dict(arch='small'), head=dict(in_channels=512)) 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/twins/twins-svt-large_16xb64_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['twins-svt-base_8xb128_in1k.py'] 2 | 3 | # model settings 4 | model = dict(backbone=dict(arch='large'), head=dict(in_channels=1024)) 5 | 6 | # dataset settings 7 | train_dataloader = dict(batch_size=64) 8 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/twins/twins-svt-small_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = ['twins-svt-base_8xb128_in1k.py'] 2 | 3 | # model settings 4 | model = dict(backbone=dict(arch='small'), head=dict(in_channels=512)) 5 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/vgg/vgg11_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/vgg11.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | # schedule settings 9 | optim_wrapper = dict(optimizer=dict(lr=0.01)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/vgg/vgg11bn_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/vgg11bn.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/vgg/vgg13_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/vgg13.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | # schedule settings 9 | optim_wrapper = dict(optimizer=dict(lr=0.01)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/vgg/vgg13bn_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/vgg13bn.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/vgg/vgg16_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/vgg16.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | # schedule settings 9 | optim_wrapper = dict(optimizer=dict(lr=0.01)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/vgg/vgg16bn_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/vgg16bn.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/vgg/vgg19_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/vgg19.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | # schedule settings 9 | optim_wrapper = dict(optimizer=dict(lr=0.01)) 10 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/vgg/vgg19bn_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/vgg19bn.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/vig/pvig-medium_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/vig/pyramid_vig_medium.py', 3 | '../_base_/datasets/imagenet_bs128_vig_224.py', 4 | '../_base_/schedules/imagenet_bs256.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/vig/pvig-small_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/vig/pyramid_vig_small.py', 3 | '../_base_/datasets/imagenet_bs128_vig_224.py', 4 | '../_base_/schedules/imagenet_bs256.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/vig/pvig-tiny_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/vig/pyramid_vig_tiny.py', 3 | '../_base_/datasets/imagenet_bs128_vig_224.py', 4 | '../_base_/schedules/imagenet_bs256.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/vig/vig-base_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/vig/vig_base.py', 3 | '../_base_/datasets/imagenet_bs128_vig_224.py', 4 | '../_base_/schedules/imagenet_bs256.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/vig/vig-small_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/vig/vig_small.py', 3 | '../_base_/datasets/imagenet_bs128_vig_224.py', 4 | '../_base_/schedules/imagenet_bs256.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/vig/vig-tiny_8xb128_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/vig/vig_tiny.py', 3 | '../_base_/datasets/imagenet_bs128_vig_224.py', 4 | '../_base_/schedules/imagenet_bs256.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/wrn/wide-resnet101_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/wide-resnet50.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | 7 | model = dict(backbone=dict(depth=101)) 8 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/wrn/wide-resnet50_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/wide-resnet50.py', 3 | '../_base_/datasets/imagenet_bs32_pil_resize.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/configs/wrn/wide-resnet50_timm_8xb32_in1k.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/wide-resnet50.py', 3 | '../_base_/datasets/imagenet_bs32_pil_bicubic.py', 4 | '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /analyze/mmpretrain_configs/readme.md: -------------------------------------------------------------------------------- 1 | ## origins 2 | copied from https://github.com/open-mmlab/mmpretrain: `version 1.1.1` 3 | 4 | -------------------------------------------------------------------------------- /assets/activation_map.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MzeroMiko/VMamba/2ed52ead062a51a64521ed3871d52914bf532876/assets/activation_map.png -------------------------------------------------------------------------------- /assets/architecture.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MzeroMiko/VMamba/2ed52ead062a51a64521ed3871d52914bf532876/assets/architecture.png -------------------------------------------------------------------------------- /assets/attn.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MzeroMiko/VMamba/2ed52ead062a51a64521ed3871d52914bf532876/assets/attn.png -------------------------------------------------------------------------------- /assets/erf.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MzeroMiko/VMamba/2ed52ead062a51a64521ed3871d52914bf532876/assets/erf.png -------------------------------------------------------------------------------- /assets/ss2d.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MzeroMiko/VMamba/2ed52ead062a51a64521ed3871d52914bf532876/assets/ss2d.png -------------------------------------------------------------------------------- /classification/configs/vssm/vmambav0_base_224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_base 4 | DROP_PATH_RATE: 0.5 5 | # DROP_PATH_RATE: 0.6 6 | VSSM: 7 | EMBED_DIM: 128 8 | DEPTHS: [ 2, 2, 27, 2 ] 9 | SSM_D_STATE: 16 10 | SSM_DT_RANK: "auto" 11 | SSM_RATIO: 2.0 12 | SSM_FORWARDTYPE: "v0" 13 | MLP_RATIO: 0.0 14 | DOWNSAMPLE: "v1" 15 | PATCHEMBED: "v1" 16 | 17 | 18 | -------------------------------------------------------------------------------- /classification/configs/vssm/vmambav0_small_224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_small 4 | DROP_PATH_RATE: 0.3 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 27, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_FORWARDTYPE: "v0" 12 | MLP_RATIO: 0.0 13 | DOWNSAMPLE: "v1" 14 | PATCHEMBED: "v1" 15 | -------------------------------------------------------------------------------- /classification/configs/vssm/vmambav0_tiny_224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 9, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_FORWARDTYPE: "v0" 12 | MLP_RATIO: 0.0 13 | DOWNSAMPLE: "v1" 14 | PATCHEMBED: "v1" 15 | -------------------------------------------------------------------------------- /classification/configs/vssm/vmambav2_base_224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_base_0229 4 | DROP_PATH_RATE: 0.6 5 | VSSM: 6 | EMBED_DIM: 128 7 | DEPTHS: [ 2, 2, 15, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | 19 | -------------------------------------------------------------------------------- /classification/configs/vssm/vmambav2_small_224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_small_0229 4 | DROP_PATH_RATE: 0.3 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 15, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssm/vmambav2_tiny_224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssm/vmambav2v_base_224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_base_0229s 4 | DROP_PATH_RATE: 0.5 5 | VSSM: 6 | EMBED_DIM: 128 7 | DEPTHS: [ 2, 2, 20, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | 19 | -------------------------------------------------------------------------------- /classification/configs/vssm/vmambav2v_small_224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_small_0229s 4 | DROP_PATH_RATE: 0.3 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 20, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssm/vmambav2v_tiny_224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230s 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav0_tiny_224_a0.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_v0 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 9, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_FORWARDTYPE: "v0" 12 | MLP_RATIO: 0.0 13 | DOWNSAMPLE: "v1" 14 | PATCHEMBED: "v1" 15 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav0_tiny_224_a01.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_a01 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 9, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_FORWARDTYPE: "v01" # csm_torch 12 | MLP_RATIO: 0.0 13 | DOWNSAMPLE: "v1" 14 | PATCHEMBED: "v1" 15 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav0_tiny_224_a0seq.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_v0seq 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 9, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_FORWARDTYPE: "v0seq" 12 | MLP_RATIO: 0.0 13 | DOWNSAMPLE: "v1" 14 | PATCHEMBED: "v1" 15 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav0_tiny_224_a1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_a1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 9, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_FORWARDTYPE: "v02" # csm_triton 12 | MLP_RATIO: 0.0 13 | DOWNSAMPLE: "v1" 14 | PATCHEMBED: "v1" 15 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav0_tiny_224_a2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_a2 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 9, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_FORWARDTYPE: "v04" # csm_triton + i16o32 12 | MLP_RATIO: 0.0 13 | DOWNSAMPLE: "v1" 14 | PATCHEMBED: "v1" -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav0_tiny_224_a3.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_a3 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 9, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_FORWARDTYPE: "v05" # csm_triton + i16o32 + noeinsum + layout 12 | MLP_RATIO: 0.0 13 | DOWNSAMPLE: "v1" 14 | PATCHEMBED: "v1" 15 | NORM_LAYER: "ln2d" 16 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav0_tiny_224_a7.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_a7 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 2, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v05" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | NORM_LAYER: "ln2d" 17 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav0_tiny_224_a7a.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_a7a 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 2, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v05" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | NORM_LAYER: "ln2d" 17 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav0_tiny_224_a8.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_a8ln 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v05" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | NORM_LAYER: "ln2d" # "ln" 17 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_a9d.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_a9d 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v05_noz" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | NORM_LAYER: "ln2d" 17 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_bidi.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230ab2d 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] # [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 # 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v052d_noz" # "v32d_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_bidi_ndw.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230ab2d_ndw 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] # [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 # 2.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v052d_noz" # "v32d_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_cas2d.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230ab2dc 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] # [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 # 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v052dc_noz" # "v32dc_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_ds16.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230_ds16 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_ds2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230_ds2 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 2 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_ds4.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230_ds4 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 4 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_ds8.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230_ds8 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 8 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.5 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_init1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230s_init1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | SSM_INIT: "v1" 19 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_init2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230s_init2 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | SSM_INIT: "v2" -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_m2s2h.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230s_m2s2h 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.5 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 2.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | # SSM_INIT: "v2" 19 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_m3s1h.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230s_m3s1h 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.5 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 3.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | # SSM_INIT: "v2" 19 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_ndw.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230s_ndw 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_ondw.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230s_ondw 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_ondwconv3_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_onone.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230s_onone 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_onnone_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_onsoftmax.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230s_ondw 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_onsoftmax_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_posndw.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230s_posndw 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | POSEMBED: true 19 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_sr1hl5.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230_sr1hl5 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.5 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_sr1l5.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230_sr1l5 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_unidi.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230ab1d 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] # [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 # 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v051d_noz" # "v31d_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/vssmab/vmambav2_tiny_224_unidi_ndw.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230ab1d_ndw 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] # [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 # 2.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v051d_noz" # "v31d_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vmambav2_tiny_224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" # v3_noz 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_base_224_a0.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_base 4 | DROP_PATH_RATE: 0.5 5 | # DROP_PATH_RATE: 0.6 6 | VSSM: 7 | EMBED_DIM: 128 8 | DEPTHS: [ 2, 2, 27, 2 ] 9 | SSM_D_STATE: 16 10 | SSM_DT_RANK: "auto" 11 | SSM_RATIO: 2.0 12 | SSM_FORWARDTYPE: "v0" 13 | MLP_RATIO: 0.0 14 | DOWNSAMPLE: "v1" 15 | PATCHEMBED: "v1" 16 | 17 | # SSM_FORWARDTYPE: "v0" # if you want exactly the same 18 | 19 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_base_224_a6.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_base_a6 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 128 7 | DEPTHS: [ 2, 2, 27, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_FORWARDTYPE: "v05" 12 | MLP_RATIO: 0.0 13 | DOWNSAMPLE: "v1" 14 | PATCHEMBED: "v1" 15 | NORM_LAYER: "ln2d" -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_base_224_aav1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_base_aav1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 128 7 | DEPTHS: [ 2, 2, 15, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_base_224_ahv3.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_base_ahv3 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 128 7 | DEPTHS: [ 2, 2, 20, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv3a_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_small_224_a0.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_small 4 | DROP_PATH_RATE: 0.3 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 27, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_FORWARDTYPE: "v0" 12 | MLP_RATIO: 0.0 13 | DOWNSAMPLE: "v1" 14 | PATCHEMBED: "v1" 15 | # SSM_FORWARDTYPE: "v0" # if you want exactly the same 16 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_small_224_a6.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_small_a6 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 27, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_FORWARDTYPE: "v05" 12 | MLP_RATIO: 0.0 13 | DOWNSAMPLE: "v1" 14 | PATCHEMBED: "v1" 15 | NORM_LAYER: "ln2d" -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_small_224_aav1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_small_aav1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 15, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_small_224_ahv3.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_small_ahv3 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 20, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv3a_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_a9v1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_a9v1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 2 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.6 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v05" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | NORM_LAYER: "ln2d" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_a9v2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_a9v2 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 4 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.6 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v05" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | NORM_LAYER: "ln2d" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_a9v3.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_a9v3 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 8 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v05" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | NORM_LAYER: "ln2d" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_aaa.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_aaa 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v05_noz_oact" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | NORM_LAYER: "ln2d" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_aav1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_aav1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_aav2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_aav2 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: true 13 | SSM_FORWARDTYPE: "v05_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_abv2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_abv2 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv2a" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_abv3.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_abv3 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv3a" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_abv4.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_abv4 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.6 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv2a" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_aca.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_aca 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_acv1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_acv1_61.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_61 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 6, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_acv1_66.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_66 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv3a_ca1" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_acv1_67.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_67 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_acv1_68.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_68 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv3a_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_acv2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv2 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv2a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_acv3.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv3 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv3a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_acv4.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv4 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.6 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv2a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_adv1_mini.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_mini 4 | DROP_PATH_RATE: 0.0 5 | VSSM: 6 | EMBED_DIM: 192 7 | DEPTHS: [12] 8 | PATCH_SIZE: 16 9 | SSM_D_STATE: 1 10 | SSM_DT_RANK: "auto" 11 | SSM_RATIO: 2.0 12 | SSM_CONV: 3 13 | SSM_CONV_BIAS: false 14 | SSM_FORWARDTYPE: "xv1a_act" 15 | MLP_RATIO: 4.0 16 | DOWNSAMPLE: "v3" 17 | PATCHEMBED: "v2" 18 | NORM_LAYER: "ln2d" 19 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_adv1_mini2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_mini 4 | DROP_PATH_RATE: 0.0 5 | VSSM: 6 | EMBED_DIM: 192 7 | DEPTHS: [36] 8 | PATCH_SIZE: 16 9 | SSM_D_STATE: 1 10 | SSM_DT_RANK: "auto" 11 | SSM_RATIO: 2.0 12 | SSM_CONV: 3 13 | SSM_CONV_BIAS: false 14 | SSM_FORWARDTYPE: "xv1a_act" 15 | MLP_RATIO: 0.0 16 | DOWNSAMPLE: "v3" 17 | PATCHEMBED: "v1" 18 | NORM_LAYER: "ln2d" 19 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_ahv3_0420.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_ahv3_0420 4 | DROP_PATH_RATE: 0.15 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv3a_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm01/vssm_tiny_224_aiv1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_aiv1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_oncnorm" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | 19 | 20 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm1/vssm_base_224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_base_0229 4 | DROP_PATH_RATE: 0.6 5 | VSSM: 6 | EMBED_DIM: 128 7 | DEPTHS: [ 2, 2, 15, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v3_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | 18 | # 89.0 + 15.2 + 118min/e + 48G 19 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm1/vssm_mini_224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0222 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v2" # "v2softmaxnozact", "v2sigmoidnozact",... 14 | MLP_RATIO: -1.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | # 17.56 + 2.73 -------------------------------------------------------------------------------- /classification/configs/wasted/vssm1/vssm_small_224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_small_0229 4 | DROP_PATH_RATE: 0.3 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 15, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v3_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | 18 | # 50.4 + 8.6 + 90min/e + 36G -------------------------------------------------------------------------------- /classification/configs/wasted/vssm1/vssm_tiny_224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.2 11 | MLP_RATIO: 4.0 12 | 13 | 14 | # PRINT_FREQ: 1 # for debug 15 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm1/vssm_tiny_224_0220.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0220 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v2" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_base_224_ahv1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_base_ahv1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 128 7 | DEPTHS: [ 2, 2, 20, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_base_224_ahv1_0421.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_base_ahv1_0421 4 | DROP_PATH_RATE: 0.5 5 | VSSM: 6 | EMBED_DIM: 128 7 | DEPTHS: [ 2, 2, 20, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_base_224_ahv1_0422.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_base_ahv1_0422 4 | DROP_PATH_RATE: 0.6 5 | VSSM: 6 | EMBED_DIM: 128 7 | DEPTHS: [ 2, 2, 20, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_base_224_aiv1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_base_aiv1 4 | DROP_PATH_RATE: 0.5 5 | VSSM: 6 | EMBED_DIM: 128 7 | DEPTHS: [ 2, 2, 20, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_oncnorm" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | 19 | 20 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_base_224_aiv1_dp06.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_base_aiv1_dp06 4 | DROP_PATH_RATE: 0.6 5 | VSSM: 6 | EMBED_DIM: 128 7 | DEPTHS: [ 2, 2, 20, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_oncnorm" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | 19 | 20 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_small_224_ahv1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_small_ahv1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 20, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_small_224_ahv1_0421.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_small_ahv1_0421 4 | DROP_PATH_RATE: 0.3 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 20, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_small_224_ahv1_0422.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_small_ahv1_0422 4 | DROP_PATH_RATE: 0.4 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 20, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_small_224_aiv1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_small_aiv1 4 | DROP_PATH_RATE: 0.3 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 20, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_oncnorm" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_small_224_aiv1_dp04.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_small_aiv1_dp04 4 | DROP_PATH_RATE: 0.4 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 20, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_oncnorm" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0211.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0211 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v2" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v2" 15 | PATCHEMBED: "v1" 16 | 17 | # PRINT_FREQ: 1 # for debug 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0211v1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0211v1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 2 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v2" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v2" 15 | PATCHEMBED: "v1" 16 | 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0212.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0212 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 64 7 | # DEPTHS: [ 4, 4, 18, 4 ] # 36 + 6.12 8 | # DEPTHS: [3, 4, 12, 4] # 30 + 4.7 9 | DEPTHS: [3, 3, 12, 3] # 26 + 4.3 10 | SSM_D_STATE: 1 11 | SSM_DT_RANK: "auto" 12 | SSM_RATIO: 2.0 13 | SSM_CONV: -1 14 | SSM_FORWARDTYPE: "v2" 15 | MLP_RATIO: 4.0 16 | DOWNSAMPLE: "v2" 17 | PATCHEMBED: "v1" -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0213.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0213 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 64 7 | DEPTHS: [3, 3, 12, 3] # 26 + 4.3 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v2" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v1" 16 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0215.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0215 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v2" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v1" 16 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0216.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0216 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v2" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0219.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0219 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_FORWARDTYPE: "v2" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0221.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0221 # to compare with 0218 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.2 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v2" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0222.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0222 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_INIT: "v1" # original: SSM_SIMPLE_INIT: true 14 | SSM_FORWARDTYPE: "v2" 15 | MLP_RATIO: 4.0 16 | DOWNSAMPLE: "v3" 17 | PATCHEMBED: "v2" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0223.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0223 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v2_nozact" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0224.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0224 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 9, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v2" 14 | MLP_RATIO: -1.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0225.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0225 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v2_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0229.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0229 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v2_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0229flex.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0229flex 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v3_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0230.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v3_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0230ab1d.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230ab1d 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v31d_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0230ab2d.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0230ab2d 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v32d_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0309.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0309 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.6 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv2_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0310.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0310 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0312.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0312 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv3_noz" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0313.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0313 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv4" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0314.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0314 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 # 128 7 | DEPTHS: [2, 2, 5, 2] # [ 2, 2, 15, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.6 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv5" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0315.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0315 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 # 128 7 | DEPTHS: [2, 2, 5, 2] # [ 2, 2, 15, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "v05" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v2" 16 | PATCHEMBED: "v1" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0316.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0316 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv4" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v2" 16 | PATCHEMBED: "v1" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0317.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0317 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 # 128 7 | DEPTHS: [2, 2, 5, 2] # [ 3,3,27,3 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv6" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v2" # "v3" 16 | PATCHEMBED: "v1" # "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0318.2.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_03182 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 # 128 7 | DEPTHS: [2, 2, 5, 2] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv61" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" # "v3" 16 | PATCHEMBED: "v2" # "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0318.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0318 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 # 128 7 | DEPTHS: [2, 2, 5, 2] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv61" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v2" # "v3" 16 | PATCHEMBED: "v1" # "v2" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0319.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0319 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 # 128 7 | DEPTHS: [2, 2, 5, 2] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv7" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" # "v3" 16 | PATCHEMBED: "v2" # "v2" 17 | NORM_LAYER: "ln2d" -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0320.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0320 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 # 128 7 | DEPTHS: [2, 2, 5, 2] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv7" 14 | GMLP: true 15 | MLP_RATIO: 2.5 16 | DOWNSAMPLE: "v3" # "v3" 17 | PATCHEMBED: "v2" # "v2" 18 | NORM_LAYER: "ln2d" 19 | 20 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0321.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0321 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 # 128 7 | DEPTHS: [2, 2, 5, 2] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" # "v3" 16 | PATCHEMBED: "v2" # "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0322.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0322 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 # 128 7 | DEPTHS: [2, 2, 5, 2] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.6 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv2a" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" # "v3" 16 | PATCHEMBED: "v2" # "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0323.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0323 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 # 128 7 | DEPTHS: [2, 2, 5, 2] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv3a" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" # "v3" 16 | PATCHEMBED: "v2" # "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0324.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0324 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 # 128 7 | DEPTHS: [2, 2, 5, 2] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv3a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" # "v3" 16 | PATCHEMBED: "v2" # "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0325.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0325 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 # 128 7 | DEPTHS: [2, 2, 5, 2] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv3a_act_mul" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" # "v3" 16 | PATCHEMBED: "v2" # "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0326.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0326 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 # 128 7 | DEPTHS: [2, 2, 5, 2] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" # "v3" 16 | PATCHEMBED: "v2" # "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_0327.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_0327 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 # 128 7 | DEPTHS: [2, 2, 5, 2] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.6 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv2a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" # "v3" 16 | PATCHEMBED: "v2" # "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.2 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v2" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v2" 15 | PATCHEMBED: "v1" 16 | 17 | 18 | # PRINT_FREQ: 1 # for debug 19 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_1v1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm1_tiny_1v1 4 | DROP_PATH_RATE: 0.1 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 4, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.2 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v2" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v2" 15 | PATCHEMBED: "v1" 16 | 17 | # PRINT_FREQ: 1 # for debug 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_a8d.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_a8d 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 0.9 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v05" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | NORM_LAYER: "ln2d" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_a9.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_a9 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.6 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v05" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | NORM_LAYER: "ln2d" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_a9a.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_a9a 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 16 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v05_noz_oact" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | NORM_LAYER: "ln2d" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_aa.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_aa 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 12 | SSM_FORWARDTYPE: "v05_noz" 13 | MLP_RATIO: 4.0 14 | DOWNSAMPLE: "v3" 15 | PATCHEMBED: "v2" 16 | NORM_LAYER: "ln2d" 17 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_abv1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_abv1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acb.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acb 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 8 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acv1_0401.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_0401 4 | DROP_PATH_RATE: 0.25 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acv1_0403.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_0403 4 | DROP_PATH_RATE: 0.15 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acv1_0405.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_0405 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | TRAIN: 19 | BASE_LR: 0.0004 20 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acv1_0406.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_0406 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | TRAIN: 19 | BASE_LR: 0.001 20 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acv1_0407.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_0407 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | TRAIN: 19 | BASE_LR: 0.002 20 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acv1_0408.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_0408 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | TRAIN: 19 | BASE_LR: 0.003 -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acv1_0409.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_0409 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | TRAIN: 19 | BASE_LR: 0.0003 -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acv1_0410.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_0410 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: -1 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | TRAIN: 19 | BASE_LR: 0.0002 -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acv1_6.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_6 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 6, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.8 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acv1_62.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_62 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acv1_62_0415.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_62_0415 4 | DROP_PATH_RATE: 0.15 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acv1_63.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_63 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acv1_64.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_64 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: 7 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_acv1_65.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_acv1_65 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_ca1" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_adv1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_adv1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_ca_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_adv1c.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_adv1c 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_aev1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_aev1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_ocov_ca_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_aev1c.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_aev1c 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_ocov_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_afv1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_afv1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_ocov2_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_agv1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_agv1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 5, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 2.0 11 | SSM_CONV: 3 # 3 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_cpos_act" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_ahv1.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_ahv1 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv1a_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | 19 | 20 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_ahv3.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_ahv3 4 | DROP_PATH_RATE: 0.2 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv3a_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/configs/wasted/vssm_tiny_224_ahv3_0418.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | TYPE: vssm 3 | NAME: vssm_tiny_ahv3_0418 4 | DROP_PATH_RATE: 0.25 5 | VSSM: 6 | EMBED_DIM: 96 7 | DEPTHS: [ 2, 2, 8, 2 ] 8 | SSM_D_STATE: 1 9 | SSM_DT_RANK: "auto" 10 | SSM_RATIO: 1.0 11 | SSM_CONV: -1 12 | SSM_CONV_BIAS: false 13 | SSM_FORWARDTYPE: "xv3a_ondwconv3" 14 | MLP_RATIO: 4.0 15 | DOWNSAMPLE: "v3" 16 | PATCHEMBED: "v2" 17 | NORM_LAYER: "ln2d" 18 | -------------------------------------------------------------------------------- /classification/data/__init__.py: -------------------------------------------------------------------------------- 1 | from .build import build_loader as _build_loader 2 | from .data_simmim_pt import build_loader_simmim 3 | from .data_simmim_ft import build_loader_finetune 4 | 5 | 6 | def build_loader(config, simmim=False, is_pretrain=False): 7 | if not simmim: 8 | return _build_loader(config) 9 | if is_pretrain: 10 | return build_loader_simmim(config) 11 | else: 12 | return build_loader_finetune(config) 13 | -------------------------------------------------------------------------------- /classification/models/mamba2/__init__.py: -------------------------------------------------------------------------------- 1 | # all the code in this folder is copied from https://github.com/state-spaces/mamba/blob/main/mamba_ssm/ops/triton/ 2 | 3 | -------------------------------------------------------------------------------- /classification/readme.md: -------------------------------------------------------------------------------- 1 | ## origins 2 | 3 | based on https://github.com/microsoft/Swin-Transformer#20240103 4 | 5 | `main.py` and `utils/utils_ema.py` is modified from https://github.com/microsoft/Swin-Transformer#20240103, based on https://github.com/facebookresearch/ConvNeXt#20240103 6 | 7 | -------------------------------------------------------------------------------- /detection/configs/mask_rcnn/mask-rcnn_r101-caffe_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask-rcnn_r50-caffe_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | depth=101, 5 | init_cfg=dict( 6 | type='Pretrained', 7 | checkpoint='open-mmlab://detectron2/resnet101_caffe'))) 8 | -------------------------------------------------------------------------------- /detection/configs/mask_rcnn/mask-rcnn_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask-rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | depth=101, 5 | init_cfg=dict(type='Pretrained', 6 | checkpoint='torchvision://resnet101'))) 7 | -------------------------------------------------------------------------------- /detection/configs/mask_rcnn/mask-rcnn_r101_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask-rcnn_r50_fpn_2x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | depth=101, 5 | init_cfg=dict(type='Pretrained', 6 | checkpoint='torchvision://resnet101'))) 7 | -------------------------------------------------------------------------------- /detection/configs/mask_rcnn/mask-rcnn_r101_fpn_8xb8-amp-lsj-200e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask-rcnn_r50_fpn_8xb8-amp-lsj-200e_coco.py' 2 | 3 | model = dict( 4 | backbone=dict( 5 | depth=101, 6 | init_cfg=dict(type='Pretrained', 7 | checkpoint='torchvision://resnet101'))) 8 | -------------------------------------------------------------------------------- /detection/configs/mask_rcnn/mask-rcnn_r101_fpn_ms-poly-3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../common/ms-poly_3x_coco-instance.py', 3 | '../_base_/models/mask-rcnn_r50_fpn.py' 4 | ] 5 | 6 | model = dict( 7 | backbone=dict( 8 | depth=101, 9 | init_cfg=dict(type='Pretrained', 10 | checkpoint='torchvision://resnet101'))) 11 | -------------------------------------------------------------------------------- /detection/configs/mask_rcnn/mask-rcnn_r18_fpn_8xb8-amp-lsj-200e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask-rcnn_r50_fpn_8xb8-amp-lsj-200e_coco.py' 2 | 3 | model = dict( 4 | backbone=dict( 5 | depth=18, 6 | init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet18')), 7 | neck=dict(in_channels=[64, 128, 256, 512])) 8 | -------------------------------------------------------------------------------- /detection/configs/mask_rcnn/mask-rcnn_r50-caffe-c4_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/mask-rcnn_r50-caffe-c4.py', 3 | '../_base_/datasets/coco_instance.py', 4 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /detection/configs/mask_rcnn/mask-rcnn_r50-caffe_fpn_ms-poly-2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask-rcnn_r50-caffe_fpn_ms-poly-1x_coco.py' 2 | 3 | train_cfg = dict(max_epochs=24) 4 | # learning rate 5 | param_scheduler = [ 6 | dict( 7 | type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500), 8 | dict( 9 | type='MultiStepLR', 10 | begin=0, 11 | end=24, 12 | by_epoch=True, 13 | milestones=[16, 22], 14 | gamma=0.1) 15 | ] 16 | -------------------------------------------------------------------------------- /detection/configs/mask_rcnn/mask-rcnn_r50-caffe_fpn_ms-poly-3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask-rcnn_r50-caffe_fpn_ms-poly-1x_coco.py' 2 | 3 | train_cfg = dict(max_epochs=36) 4 | # learning rate 5 | param_scheduler = [ 6 | dict( 7 | type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500), 8 | dict( 9 | type='MultiStepLR', 10 | begin=0, 11 | end=24, 12 | by_epoch=True, 13 | milestones=[28, 34], 14 | gamma=0.1) 15 | ] 16 | -------------------------------------------------------------------------------- /detection/configs/mask_rcnn/mask-rcnn_r50_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/mask-rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_instance.py', 4 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /detection/configs/mask_rcnn/mask-rcnn_r50_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/mask-rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_instance.py', 4 | '../_base_/schedules/schedule_2x.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /detection/configs/mask_rcnn/mask-rcnn_r50_fpn_amp-1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask-rcnn_r50_fpn_1x_coco.py' 2 | 3 | # Enable automatic-mixed-precision training with AmpOptimWrapper. 4 | optim_wrapper = dict(type='AmpOptimWrapper') 5 | -------------------------------------------------------------------------------- /detection/configs/mask_rcnn/mask-rcnn_r50_fpn_ms-poly-3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../common/ms-poly_3x_coco-instance.py', 3 | '../_base_/models/mask-rcnn_r50_fpn.py' 4 | ] 5 | -------------------------------------------------------------------------------- /detection/configs/swin/mask-rcnn_swin-s-p4-w7_fpn_amp-ms-crop-3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask-rcnn_swin-t-p4-w7_fpn_amp-ms-crop-3x_coco.py' 2 | pretrained = 'https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_small_patch4_window7_224.pth' # noqa 3 | model = dict( 4 | backbone=dict( 5 | depths=[2, 2, 18, 2], 6 | init_cfg=dict(type='Pretrained', checkpoint=pretrained))) 7 | -------------------------------------------------------------------------------- /detection/configs/swin/mask-rcnn_swin-t-p4-w7_fpn_amp-ms-crop-3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask-rcnn_swin-t-p4-w7_fpn_ms-crop-3x_coco.py' 2 | # Enable automatic-mixed-precision training with AmpOptimWrapper. 3 | optim_wrapper = dict(type='AmpOptimWrapper') 4 | -------------------------------------------------------------------------------- /detection/readme.md: -------------------------------------------------------------------------------- 1 | ## origins 2 | `configs/` and `tools/` are copied from https://github.com/open-mmlab/mmdetection: `version 3.3.0` 3 | 4 | 5 | ## modifications 6 | `tools/train.py#12` is added with `import model` 7 | `tools/test.py#17` is added with `import model` 8 | 9 | -------------------------------------------------------------------------------- /detection/tools/analysis_tools/mot/dist_mot_search.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | CONFIG=$1 4 | GPUS=$2 5 | PORT=${PORT:-29500} 6 | 7 | PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \ 8 | python -m torch.distributed.launch --nproc_per_node=$GPUS --master_port=$PORT \ 9 | $(dirname "$0")/mot_param_search.py $CONFIG --launcher pytorch ${@:3} 10 | -------------------------------------------------------------------------------- /detection/tools/dataset_converters/scripts/preprocess_voc2007.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | DOWNLOAD_DIR=$1 4 | DATA_ROOT=$2 5 | 6 | tar -xvf $DOWNLOAD_DIR/OpenDataLab___PASCAL_VOC2007/raw/VOCtrainval_06-Nov-2007.tar -C $DATA_ROOT 7 | tar -xvf $DOWNLOAD_DIR/OpenDataLab___PASCAL_VOC2007/raw/VOCtestnoimgs_06-Nov-2007.tar -C $DATA_ROOT 8 | rm -rf $DOWNLOAD_DIR/OpenDataLab___PASCAL_VOC2007 9 | -------------------------------------------------------------------------------- /detection/tools/dataset_converters/scripts/preprocess_voc2012.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | DOWNLOAD_DIR=$1 4 | DATA_ROOT=$2 5 | 6 | tar -xvf $DOWNLOAD_DIR/OpenDataLab___PASCAL_VOC2012/raw/VOCtrainval_11-May-2012.tar -C $DATA_ROOT 7 | tar -xvf $DOWNLOAD_DIR/OpenDataLab___PASCAL_VOC2012/raw/VOC2012test.tar -C $DATA_ROOT 8 | rm -rf $DOWNLOAD_DIR/OpenDataLab___PASCAL_VOC2012 9 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | torch # for full alignment 2.2.0 2 | torchvision 3 | torchaudio 4 | packaging 5 | triton 6 | timm==0.4.12 7 | pytest 8 | chardet 9 | yacs 10 | termcolor 11 | submitit 12 | tensorboardX 13 | fvcore 14 | seaborn 15 | # timm==0.5.4 # for s4nd 16 | # hydra-core # for s4nd 17 | # pytorch_lightning # for s4nd 18 | -------------------------------------------------------------------------------- /segmentation/configs/swin/swin-base-patch4-window12-in22k-384x384-pre_upernet_8xb2-160k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | './swin-base-patch4-window12-in1k-384x384-pre_upernet_8xb2-160k_ade20k-512x512.py' # noqa 3 | ] 4 | checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_base_patch4_window12_384_22k_20220317-e5c09f74.pth' # noqa 5 | model = dict( 6 | backbone=dict( 7 | init_cfg=dict(type='Pretrained', checkpoint=checkpoint_file))) 8 | -------------------------------------------------------------------------------- /segmentation/configs/swin/swin-base-patch4-window7-in22k-pre_upernet_8xb2-160k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | './swin-base-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py' 3 | ] 4 | checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_base_patch4_window7_224_22k_20220317-4f79f7c0.pth' # noqa 5 | model = dict( 6 | backbone=dict( 7 | init_cfg=dict(type='Pretrained', checkpoint=checkpoint_file))) 8 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r101_4xb2-40k_cityscapes-512x1024.py: -------------------------------------------------------------------------------- 1 | _base_ = './upernet_r50_4xb2-40k_cityscapes-512x1024.py' 2 | model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r101_4xb2-40k_cityscapes-769x769.py: -------------------------------------------------------------------------------- 1 | _base_ = './upernet_r50_4xb2-40k_cityscapes-769x769.py' 2 | model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r101_4xb2-80k_cityscapes-512x1024.py: -------------------------------------------------------------------------------- 1 | _base_ = './upernet_r50_4xb2-80k_cityscapes-512x1024.py' 2 | model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r101_4xb2-80k_cityscapes-769x769.py: -------------------------------------------------------------------------------- 1 | _base_ = './upernet_r50_4xb2-80k_cityscapes-769x769.py' 2 | model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r101_4xb4-160k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = './upernet_r50_4xb4-160k_ade20k-512x512.py' 2 | model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r101_4xb4-20k_voc12aug-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = './upernet_r50_4xb4-20k_voc12aug-512x512.py' 2 | model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r101_4xb4-40k_voc12aug-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = './upernet_r50_4xb4-40k_voc12aug-512x512.py' 2 | model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r101_4xb4-80k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = './upernet_r50_4xb4-80k_ade20k-512x512.py' 2 | model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r18_4xb2-40k_cityscapes-512x1024.py: -------------------------------------------------------------------------------- 1 | _base_ = './upernet_r50_4xb2-40k_cityscapes-512x1024.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnet18_v1c', 4 | backbone=dict(depth=18), 5 | decode_head=dict(in_channels=[64, 128, 256, 512]), 6 | auxiliary_head=dict(in_channels=256)) 7 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r18_4xb2-80k_cityscapes-512x1024.py: -------------------------------------------------------------------------------- 1 | _base_ = './upernet_r50_4xb2-80k_cityscapes-512x1024.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnet18_v1c', 4 | backbone=dict(depth=18), 5 | decode_head=dict(in_channels=[64, 128, 256, 512]), 6 | auxiliary_head=dict(in_channels=256)) 7 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r18_4xb4-160k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/upernet_r50.py', '../_base_/datasets/ade20k.py', 3 | '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py' 4 | ] 5 | model = dict( 6 | pretrained='open-mmlab://resnet18_v1c', 7 | backbone=dict(depth=18), 8 | decode_head=dict(in_channels=[64, 128, 256, 512], num_classes=150), 9 | auxiliary_head=dict(in_channels=256, num_classes=150)) 10 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r18_4xb4-20k_voc12aug-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/upernet_r50.py', 3 | '../_base_/datasets/pascal_voc12_aug.py', '../_base_/default_runtime.py', 4 | '../_base_/schedules/schedule_20k.py' 5 | ] 6 | model = dict( 7 | pretrained='open-mmlab://resnet18_v1c', 8 | backbone=dict(depth=18), 9 | decode_head=dict(in_channels=[64, 128, 256, 512], num_classes=21), 10 | auxiliary_head=dict(in_channels=256, num_classes=21)) 11 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r18_4xb4-40k_voc12aug-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/upernet_r50.py', 3 | '../_base_/datasets/pascal_voc12_aug.py', '../_base_/default_runtime.py', 4 | '../_base_/schedules/schedule_40k.py' 5 | ] 6 | model = dict( 7 | pretrained='open-mmlab://resnet18_v1c', 8 | backbone=dict(depth=18), 9 | decode_head=dict(in_channels=[64, 128, 256, 512], num_classes=21), 10 | auxiliary_head=dict(in_channels=256, num_classes=21)) 11 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r18_4xb4-80k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/upernet_r50.py', '../_base_/datasets/ade20k.py', 3 | '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py' 4 | ] 5 | model = dict( 6 | pretrained='open-mmlab://resnet18_v1c', 7 | backbone=dict(depth=18), 8 | decode_head=dict(in_channels=[64, 128, 256, 512], num_classes=150), 9 | auxiliary_head=dict(in_channels=256, num_classes=150)) 10 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r50_4xb2-40k_cityscapes-512x1024.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/upernet_r50.py', '../_base_/datasets/cityscapes.py', 3 | '../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py' 4 | ] 5 | crop_size = (512, 1024) 6 | data_preprocessor = dict(size=crop_size) 7 | model = dict(data_preprocessor=data_preprocessor) 8 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r50_4xb2-80k_cityscapes-512x1024.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/upernet_r50.py', '../_base_/datasets/cityscapes.py', 3 | '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py' 4 | ] 5 | crop_size = (512, 1024) 6 | data_preprocessor = dict(size=crop_size) 7 | model = dict(data_preprocessor=data_preprocessor) 8 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r50_4xb4-160k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/upernet_r50.py', '../_base_/datasets/ade20k.py', 3 | '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py' 4 | ] 5 | crop_size = (512, 512) 6 | data_preprocessor = dict(size=crop_size) 7 | model = dict( 8 | data_preprocessor=data_preprocessor, 9 | decode_head=dict(num_classes=150), 10 | auxiliary_head=dict(num_classes=150)) 11 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r50_4xb4-20k_voc12aug-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/upernet_r50.py', 3 | '../_base_/datasets/pascal_voc12_aug.py', '../_base_/default_runtime.py', 4 | '../_base_/schedules/schedule_20k.py' 5 | ] 6 | crop_size = (512, 512) 7 | data_preprocessor = dict(size=crop_size) 8 | model = dict( 9 | data_preprocessor=data_preprocessor, 10 | decode_head=dict(num_classes=21), 11 | auxiliary_head=dict(num_classes=21)) 12 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r50_4xb4-40k_voc12aug-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/upernet_r50.py', 3 | '../_base_/datasets/pascal_voc12_aug.py', '../_base_/default_runtime.py', 4 | '../_base_/schedules/schedule_40k.py' 5 | ] 6 | crop_size = (512, 512) 7 | data_preprocessor = dict(size=crop_size) 8 | model = dict( 9 | data_preprocessor=data_preprocessor, 10 | decode_head=dict(num_classes=21), 11 | auxiliary_head=dict(num_classes=21)) 12 | -------------------------------------------------------------------------------- /segmentation/configs/upernet/upernet_r50_4xb4-80k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/upernet_r50.py', '../_base_/datasets/ade20k.py', 3 | '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py' 4 | ] 5 | crop_size = (512, 512) 6 | data_preprocessor = dict(size=crop_size) 7 | model = dict( 8 | data_preprocessor=data_preprocessor, 9 | decode_head=dict(num_classes=150), 10 | auxiliary_head=dict(num_classes=150)) 11 | -------------------------------------------------------------------------------- /segmentation/configs/vit/vit_deit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = './vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py' 2 | 3 | model = dict( 4 | pretrained='pretrain/deit_base_patch16_224-b5f2ef4d.pth', 5 | backbone=dict(drop_path_rate=0.1, final_norm=True)) 6 | -------------------------------------------------------------------------------- /segmentation/configs/vit/vit_deit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = './vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py' 2 | 3 | model = dict( 4 | pretrained='pretrain/deit_base_patch16_224-b5f2ef4d.pth', 5 | backbone=dict(drop_path_rate=0.1), 6 | ) 7 | -------------------------------------------------------------------------------- /segmentation/configs/vit/vit_deit-b16_upernet_8xb2-160k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = './vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py' 2 | 3 | model = dict( 4 | pretrained='pretrain/deit_base_patch16_224-b5f2ef4d.pth', 5 | backbone=dict(drop_path_rate=0.1), 6 | neck=None) 7 | -------------------------------------------------------------------------------- /segmentation/configs/vit/vit_deit-b16_upernet_8xb2-80k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = './vit_vit-b16_mln_upernet_8xb2-80k_ade20k-512x512.py' 2 | 3 | model = dict( 4 | pretrained='pretrain/deit_base_patch16_224-b5f2ef4d.pth', 5 | backbone=dict(drop_path_rate=0.1), 6 | neck=None) 7 | -------------------------------------------------------------------------------- /segmentation/configs/vit/vit_deit-s16_mln_upernet_8xb2-160k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = './vit_vit-b16_mln_upernet_8xb2-160k_ade20k-512x512.py' 2 | 3 | model = dict( 4 | pretrained='pretrain/deit_small_patch16_224-cd65a155.pth', 5 | backbone=dict(num_heads=6, embed_dims=384, drop_path_rate=0.1), 6 | decode_head=dict(num_classes=150, in_channels=[384, 384, 384, 384]), 7 | neck=dict(in_channels=[384, 384, 384, 384], out_channels=384), 8 | auxiliary_head=dict(num_classes=150, in_channels=384)) 9 | -------------------------------------------------------------------------------- /segmentation/configs/vit/vit_deit-s16_upernet_8xb2-160k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = './vit_vit-b16_mln_upernet_8xb2-80k_ade20k-512x512.py' 2 | 3 | model = dict( 4 | pretrained='pretrain/deit_small_patch16_224-cd65a155.pth', 5 | backbone=dict(num_heads=6, embed_dims=384, drop_path_rate=0.1), 6 | decode_head=dict(num_classes=150, in_channels=[384, 384, 384, 384]), 7 | neck=None, 8 | auxiliary_head=dict(num_classes=150, in_channels=384)) 9 | -------------------------------------------------------------------------------- /segmentation/configs/vit/vit_deit-s16_upernet_8xb2-80k_ade20k-512x512.py: -------------------------------------------------------------------------------- 1 | _base_ = './vit_vit-b16_mln_upernet_8xb2-80k_ade20k-512x512.py' 2 | 3 | model = dict( 4 | pretrained='pretrain/deit_small_patch16_224-cd65a155.pth', 5 | backbone=dict(num_heads=6, embed_dims=384, drop_path_rate=0.1), 6 | decode_head=dict(num_classes=150, in_channels=[384, 384, 384, 384]), 7 | neck=None, 8 | auxiliary_head=dict(num_classes=150, in_channels=384)) 9 | -------------------------------------------------------------------------------- /segmentation/readme.md: -------------------------------------------------------------------------------- 1 | ## origins 2 | `configs/` and `tools/` are copied from https://github.com/open-mmlab/mmsegmentation: `version 1.2.2` 3 | 4 | ## modifications 5 | `tools/train.py#13` is added with `import model` 6 | `tools/test.py#8` is added with `import model` 7 | 8 | --------------------------------------------------------------------------------