├── .DS_Store ├── .gitignore ├── LICENSE.txt ├── README.md ├── assets ├── vim_pipeline_v1.9.png └── vim_teaser_v1.7.png ├── causal-conv1d ├── AUTHORS ├── LICENSE ├── README.md ├── causal_conv1d │ ├── __init__.py │ └── causal_conv1d_interface.py ├── csrc │ ├── causal_conv1d.cpp │ ├── causal_conv1d.h │ ├── causal_conv1d_bwd.cu │ ├── causal_conv1d_common.h │ ├── causal_conv1d_fwd.cu │ ├── causal_conv1d_update.cu │ └── static_switch.h ├── setup.py └── tests │ └── test_causal_conv1d.py ├── det ├── .circleci │ ├── config.yml │ └── import-tests.sh ├── .clang-format ├── .flake8 ├── .gitignore ├── GETTING_STARTED.md ├── INSTALL.md ├── LICENSE ├── MODEL_ZOO.md ├── README.md ├── configs │ ├── Base-RCNN-C4.yaml │ ├── Base-RCNN-DilatedC5.yaml │ ├── Base-RCNN-FPN.yaml │ ├── Base-RetinaNet.yaml │ ├── COCO-Detection │ │ ├── fast_rcnn_R_50_FPN_1x.yaml │ │ ├── faster_rcnn_R_101_C4_3x.yaml │ │ ├── faster_rcnn_R_101_DC5_3x.yaml │ │ ├── faster_rcnn_R_101_FPN_3x.yaml │ │ ├── faster_rcnn_R_50_C4_1x.yaml │ │ ├── faster_rcnn_R_50_C4_3x.yaml │ │ ├── faster_rcnn_R_50_DC5_1x.yaml │ │ ├── faster_rcnn_R_50_DC5_3x.yaml │ │ ├── faster_rcnn_R_50_FPN_1x.yaml │ │ ├── faster_rcnn_R_50_FPN_3x.yaml │ │ ├── faster_rcnn_X_101_32x8d_FPN_3x.yaml │ │ ├── fcos_R_50_FPN_1x.py │ │ ├── retinanet_R_101_FPN_3x.yaml │ │ ├── retinanet_R_50_FPN_1x.py │ │ ├── retinanet_R_50_FPN_1x.yaml │ │ ├── retinanet_R_50_FPN_3x.yaml │ │ ├── rpn_R_50_C4_1x.yaml │ │ └── rpn_R_50_FPN_1x.yaml │ ├── COCO-InstanceSegmentation │ │ ├── mask_rcnn_R_101_C4_3x.yaml │ │ ├── mask_rcnn_R_101_DC5_3x.yaml │ │ ├── mask_rcnn_R_101_FPN_3x.yaml │ │ ├── mask_rcnn_R_50_C4_1x.py │ │ ├── mask_rcnn_R_50_C4_1x.yaml │ │ ├── mask_rcnn_R_50_C4_3x.yaml │ │ ├── mask_rcnn_R_50_DC5_1x.yaml │ │ ├── mask_rcnn_R_50_DC5_3x.yaml │ │ ├── mask_rcnn_R_50_FPN_1x.py │ │ ├── mask_rcnn_R_50_FPN_1x.yaml │ │ ├── mask_rcnn_R_50_FPN_1x_giou.yaml │ │ ├── mask_rcnn_R_50_FPN_3x.yaml │ │ ├── mask_rcnn_X_101_32x8d_FPN_3x.yaml │ │ ├── mask_rcnn_regnetx_4gf_dds_fpn_1x.py │ │ └── mask_rcnn_regnety_4gf_dds_fpn_1x.py │ ├── COCO-Keypoints │ │ ├── Base-Keypoint-RCNN-FPN.yaml │ │ ├── keypoint_rcnn_R_101_FPN_3x.yaml │ │ ├── keypoint_rcnn_R_50_FPN_1x.py │ │ ├── keypoint_rcnn_R_50_FPN_1x.yaml │ │ ├── keypoint_rcnn_R_50_FPN_3x.yaml │ │ └── keypoint_rcnn_X_101_32x8d_FPN_3x.yaml │ ├── COCO-PanopticSegmentation │ │ ├── Base-Panoptic-FPN.yaml │ │ ├── panoptic_fpn_R_101_3x.yaml │ │ ├── panoptic_fpn_R_50_1x.py │ │ ├── panoptic_fpn_R_50_1x.yaml │ │ └── panoptic_fpn_R_50_3x.yaml │ ├── Cityscapes │ │ └── mask_rcnn_R_50_FPN.yaml │ ├── Detectron1-Comparisons │ │ ├── README.md │ │ ├── faster_rcnn_R_50_FPN_noaug_1x.yaml │ │ ├── keypoint_rcnn_R_50_FPN_1x.yaml │ │ └── mask_rcnn_R_50_FPN_noaug_1x.yaml │ ├── LVISv0.5-InstanceSegmentation │ │ ├── mask_rcnn_R_101_FPN_1x.yaml │ │ ├── mask_rcnn_R_50_FPN_1x.yaml │ │ └── mask_rcnn_X_101_32x8d_FPN_1x.yaml │ ├── LVISv1-InstanceSegmentation │ │ ├── mask_rcnn_R_101_FPN_1x.yaml │ │ ├── mask_rcnn_R_50_FPN_1x.yaml │ │ └── mask_rcnn_X_101_32x8d_FPN_1x.yaml │ ├── Misc │ │ ├── cascade_mask_rcnn_R_50_FPN_1x.yaml │ │ ├── cascade_mask_rcnn_R_50_FPN_3x.yaml │ │ ├── cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv.yaml │ │ ├── mask_rcnn_R_50_FPN_1x_cls_agnostic.yaml │ │ ├── mask_rcnn_R_50_FPN_1x_dconv_c3-c5.yaml │ │ ├── mask_rcnn_R_50_FPN_3x_dconv_c3-c5.yaml │ │ ├── mask_rcnn_R_50_FPN_3x_gn.yaml │ │ ├── mask_rcnn_R_50_FPN_3x_syncbn.yaml │ │ ├── mmdet_mask_rcnn_R_50_FPN_1x.py │ │ ├── panoptic_fpn_R_101_dconv_cascade_gn_3x.yaml │ │ ├── scratch_mask_rcnn_R_50_FPN_3x_gn.yaml │ │ ├── scratch_mask_rcnn_R_50_FPN_9x_gn.yaml │ │ ├── scratch_mask_rcnn_R_50_FPN_9x_syncbn.yaml │ │ ├── semantic_R_50_FPN_1x.yaml │ │ └── torchvision_imagenet_R_50.py │ ├── PascalVOC-Detection │ │ ├── faster_rcnn_R_50_C4.yaml │ │ └── faster_rcnn_R_50_FPN.yaml │ ├── common │ │ ├── README.md │ │ ├── coco_schedule.py │ │ ├── data │ │ │ ├── coco.py │ │ │ ├── coco_keypoint.py │ │ │ ├── coco_panoptic_separated.py │ │ │ └── constants.py │ │ ├── models │ │ │ ├── cascade_rcnn.py │ │ │ ├── fcos.py │ │ │ ├── keypoint_rcnn_fpn.py │ │ │ ├── mask_rcnn_c4.py │ │ │ ├── mask_rcnn_fpn.py │ │ │ ├── mask_rcnn_vimdet.py │ │ │ ├── mask_rcnn_vitdet.py │ │ │ ├── panoptic_fpn.py │ │ │ └── retinanet.py │ │ ├── optim.py │ │ └── train.py │ ├── new_baselines │ │ ├── mask_rcnn_R_101_FPN_100ep_LSJ.py │ │ ├── mask_rcnn_R_101_FPN_200ep_LSJ.py │ │ ├── mask_rcnn_R_101_FPN_400ep_LSJ.py │ │ ├── mask_rcnn_R_50_FPN_100ep_LSJ.py │ │ ├── mask_rcnn_R_50_FPN_200ep_LSJ.py │ │ ├── mask_rcnn_R_50_FPN_400ep_LSJ.py │ │ ├── mask_rcnn_R_50_FPN_50ep_LSJ.py │ │ ├── mask_rcnn_regnetx_4gf_dds_FPN_100ep_LSJ.py │ │ ├── mask_rcnn_regnetx_4gf_dds_FPN_200ep_LSJ.py │ │ ├── mask_rcnn_regnetx_4gf_dds_FPN_400ep_LSJ.py │ │ ├── mask_rcnn_regnety_4gf_dds_FPN_100ep_LSJ.py │ │ ├── mask_rcnn_regnety_4gf_dds_FPN_200ep_LSJ.py │ │ └── mask_rcnn_regnety_4gf_dds_FPN_400ep_LSJ.py │ └── quick_schedules │ │ ├── README.md │ │ ├── cascade_mask_rcnn_R_50_FPN_inference_acc_test.yaml │ │ ├── cascade_mask_rcnn_R_50_FPN_instant_test.yaml │ │ ├── fast_rcnn_R_50_FPN_inference_acc_test.yaml │ │ ├── fast_rcnn_R_50_FPN_instant_test.yaml │ │ ├── keypoint_rcnn_R_50_FPN_inference_acc_test.yaml │ │ ├── keypoint_rcnn_R_50_FPN_instant_test.yaml │ │ ├── keypoint_rcnn_R_50_FPN_normalized_training_acc_test.yaml │ │ ├── keypoint_rcnn_R_50_FPN_training_acc_test.yaml │ │ ├── mask_rcnn_R_50_C4_GCV_instant_test.yaml │ │ ├── mask_rcnn_R_50_C4_inference_acc_test.yaml │ │ ├── mask_rcnn_R_50_C4_instant_test.yaml │ │ ├── mask_rcnn_R_50_C4_training_acc_test.yaml │ │ ├── mask_rcnn_R_50_DC5_inference_acc_test.yaml │ │ ├── mask_rcnn_R_50_FPN_inference_acc_test.yaml │ │ ├── mask_rcnn_R_50_FPN_instant_test.yaml │ │ ├── mask_rcnn_R_50_FPN_pred_boxes_training_acc_test.yaml │ │ ├── mask_rcnn_R_50_FPN_training_acc_test.yaml │ │ ├── panoptic_fpn_R_50_inference_acc_test.yaml │ │ ├── panoptic_fpn_R_50_instant_test.yaml │ │ ├── panoptic_fpn_R_50_training_acc_test.yaml │ │ ├── retinanet_R_50_FPN_inference_acc_test.yaml │ │ ├── retinanet_R_50_FPN_instant_test.yaml │ │ ├── rpn_R_50_FPN_inference_acc_test.yaml │ │ ├── rpn_R_50_FPN_instant_test.yaml │ │ ├── semantic_R_50_FPN_inference_acc_test.yaml │ │ ├── semantic_R_50_FPN_instant_test.yaml │ │ └── semantic_R_50_FPN_training_acc_test.yaml ├── datasets │ ├── README.md │ ├── prepare_ade20k_sem_seg.py │ ├── prepare_cocofied_lvis.py │ ├── prepare_for_tests.sh │ └── prepare_panoptic_fpn.py ├── demo │ ├── README.md │ ├── demo.py │ └── predictor.py ├── det-requirements.txt ├── detectron2 │ ├── __init__.py │ ├── checkpoint │ │ ├── __init__.py │ │ ├── c2_model_loading.py │ │ ├── catalog.py │ │ └── detection_checkpoint.py │ ├── config │ │ ├── __init__.py │ │ ├── compat.py │ │ ├── config.py │ │ ├── defaults.py │ │ ├── instantiate.py │ │ └── lazy.py │ ├── data │ │ ├── __init__.py │ │ ├── benchmark.py │ │ ├── build.py │ │ ├── catalog.py │ │ ├── common.py │ │ ├── dataset_mapper.py │ │ ├── datasets │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── builtin.py │ │ │ ├── builtin_meta.py │ │ │ ├── cityscapes.py │ │ │ ├── cityscapes_panoptic.py │ │ │ ├── coco.py │ │ │ ├── coco_panoptic.py │ │ │ ├── lvis.py │ │ │ ├── lvis_v0_5_categories.py │ │ │ ├── lvis_v1_categories.py │ │ │ ├── lvis_v1_category_image_count.py │ │ │ ├── pascal_voc.py │ │ │ └── register_coco.py │ │ ├── detection_utils.py │ │ ├── samplers │ │ │ ├── __init__.py │ │ │ ├── distributed_sampler.py │ │ │ └── grouped_batch_sampler.py │ │ └── transforms │ │ │ ├── __init__.py │ │ │ ├── augmentation.py │ │ │ ├── augmentation_impl.py │ │ │ └── transform.py │ ├── engine │ │ ├── __init__.py │ │ ├── defaults.py │ │ ├── hooks.py │ │ ├── launch.py │ │ └── train_loop.py │ ├── evaluation │ │ ├── __init__.py │ │ ├── cityscapes_evaluation.py │ │ ├── coco_evaluation.py │ │ ├── evaluator.py │ │ ├── fast_eval_api.py │ │ ├── lvis_evaluation.py │ │ ├── panoptic_evaluation.py │ │ ├── pascal_voc_evaluation.py │ │ ├── rotated_coco_evaluation.py │ │ ├── sem_seg_evaluation.py │ │ └── testing.py │ ├── export │ │ ├── README.md │ │ ├── __init__.py │ │ ├── api.py │ │ ├── c10.py │ │ ├── caffe2_export.py │ │ ├── caffe2_inference.py │ │ ├── caffe2_modeling.py │ │ ├── caffe2_patch.py │ │ ├── flatten.py │ │ ├── shared.py │ │ ├── torchscript.py │ │ └── torchscript_patch.py │ ├── layers │ │ ├── __init__.py │ │ ├── aspp.py │ │ ├── batch_norm.py │ │ ├── blocks.py │ │ ├── csrc │ │ │ ├── README.md │ │ │ ├── ROIAlignRotated │ │ │ │ ├── ROIAlignRotated.h │ │ │ │ ├── ROIAlignRotated_cpu.cpp │ │ │ │ └── ROIAlignRotated_cuda.cu │ │ │ ├── box_iou_rotated │ │ │ │ ├── box_iou_rotated.h │ │ │ │ ├── box_iou_rotated_cpu.cpp │ │ │ │ ├── box_iou_rotated_cuda.cu │ │ │ │ └── box_iou_rotated_utils.h │ │ │ ├── cocoeval │ │ │ │ ├── cocoeval.cpp │ │ │ │ └── cocoeval.h │ │ │ ├── cuda_version.cu │ │ │ ├── deformable │ │ │ │ ├── deform_conv.h │ │ │ │ ├── deform_conv_cuda.cu │ │ │ │ └── deform_conv_cuda_kernel.cu │ │ │ ├── nms_rotated │ │ │ │ ├── nms_rotated.h │ │ │ │ ├── nms_rotated_cpu.cpp │ │ │ │ └── nms_rotated_cuda.cu │ │ │ └── vision.cpp │ │ ├── deform_conv.py │ │ ├── losses.py │ │ ├── mask_ops.py │ │ ├── nms.py │ │ ├── roi_align.py │ │ ├── roi_align_rotated.py │ │ ├── rotated_boxes.py │ │ ├── shape_spec.py │ │ └── wrappers.py │ ├── model_zoo │ │ ├── __init__.py │ │ └── model_zoo.py │ ├── modeling │ │ ├── __init__.py │ │ ├── anchor_generator.py │ │ ├── backbone │ │ │ ├── __init__.py │ │ │ ├── backbone.py │ │ │ ├── build.py │ │ │ ├── fpn.py │ │ │ ├── mvit.py │ │ │ ├── regnet.py │ │ │ ├── resnet.py │ │ │ ├── swin.py │ │ │ ├── utils.py │ │ │ ├── vim.py │ │ │ └── vit.py │ │ ├── box_regression.py │ │ ├── matcher.py │ │ ├── meta_arch │ │ │ ├── __init__.py │ │ │ ├── build.py │ │ │ ├── dense_detector.py │ │ │ ├── fcos.py │ │ │ ├── panoptic_fpn.py │ │ │ ├── rcnn.py │ │ │ ├── retinanet.py │ │ │ └── semantic_seg.py │ │ ├── mmdet_wrapper.py │ │ ├── poolers.py │ │ ├── postprocessing.py │ │ ├── proposal_generator │ │ │ ├── __init__.py │ │ │ ├── build.py │ │ │ ├── proposal_utils.py │ │ │ ├── rpn.py │ │ │ └── rrpn.py │ │ ├── roi_heads │ │ │ ├── __init__.py │ │ │ ├── box_head.py │ │ │ ├── cascade_rcnn.py │ │ │ ├── fast_rcnn.py │ │ │ ├── keypoint_head.py │ │ │ ├── mask_head.py │ │ │ ├── roi_heads.py │ │ │ └── rotated_fast_rcnn.py │ │ ├── sampling.py │ │ └── test_time_augmentation.py │ ├── projects │ │ ├── README.md │ │ └── __init__.py │ ├── solver │ │ ├── __init__.py │ │ ├── build.py │ │ └── lr_scheduler.py │ ├── structures │ │ ├── __init__.py │ │ ├── boxes.py │ │ ├── image_list.py │ │ ├── instances.py │ │ ├── keypoints.py │ │ ├── masks.py │ │ └── rotated_boxes.py │ ├── tracking │ │ ├── __init__.py │ │ ├── base_tracker.py │ │ ├── bbox_iou_tracker.py │ │ ├── hungarian_tracker.py │ │ ├── iou_weighted_hungarian_bbox_iou_tracker.py │ │ ├── utils.py │ │ └── vanilla_hungarian_bbox_iou_tracker.py │ └── utils │ │ ├── README.md │ │ ├── __init__.py │ │ ├── analysis.py │ │ ├── collect_env.py │ │ ├── colormap.py │ │ ├── comm.py │ │ ├── develop.py │ │ ├── env.py │ │ ├── events.py │ │ ├── file_io.py │ │ ├── logger.py │ │ ├── memory.py │ │ ├── registry.py │ │ ├── serialize.py │ │ ├── testing.py │ │ ├── tracing.py │ │ ├── video_visualizer.py │ │ └── visualizer.py ├── dev │ ├── README.md │ ├── linter.sh │ ├── packaging │ │ ├── README.md │ │ ├── build_all_wheels.sh │ │ ├── build_wheel.sh │ │ ├── gen_install_table.py │ │ ├── gen_wheel_index.sh │ │ └── pkg_helpers.bash │ ├── parse_results.sh │ ├── run_inference_tests.sh │ └── run_instant_tests.sh ├── docker │ ├── Dockerfile │ ├── README.md │ ├── deploy.Dockerfile │ └── docker-compose.yml ├── docs │ ├── .gitignore │ ├── Makefile │ ├── README.md │ ├── _static │ │ └── css │ │ │ └── custom.css │ ├── conf.py │ ├── index.rst │ ├── modules │ │ ├── checkpoint.rst │ │ ├── config.rst │ │ ├── data.rst │ │ ├── data_transforms.rst │ │ ├── engine.rst │ │ ├── evaluation.rst │ │ ├── export.rst │ │ ├── fvcore.rst │ │ ├── index.rst │ │ ├── layers.rst │ │ ├── model_zoo.rst │ │ ├── modeling.rst │ │ ├── solver.rst │ │ ├── structures.rst │ │ └── utils.rst │ ├── notes │ │ ├── benchmarks.md │ │ ├── changelog.md │ │ ├── compatibility.md │ │ ├── contributing.md │ │ └── index.rst │ ├── requirements.txt │ └── tutorials │ │ ├── README.md │ │ ├── augmentation.md │ │ ├── builtin_datasets.md │ │ ├── configs.md │ │ ├── data_loading.md │ │ ├── datasets.md │ │ ├── deployment.md │ │ ├── evaluation.md │ │ ├── extend.md │ │ ├── getting_started.md │ │ ├── index.rst │ │ ├── install.md │ │ ├── lazyconfigs.md │ │ ├── models.md │ │ ├── training.md │ │ └── write-models.md ├── projects │ ├── DeepLab │ │ ├── README.md │ │ ├── configs │ │ │ └── Cityscapes-SemanticSegmentation │ │ │ │ ├── Base-DeepLabV3-OS16-Semantic.yaml │ │ │ │ ├── deeplab_v3_R_103_os16_mg124_poly_90k_bs16.yaml │ │ │ │ └── deeplab_v3_plus_R_103_os16_mg124_poly_90k_bs16.yaml │ │ ├── deeplab │ │ │ ├── __init__.py │ │ │ ├── build_solver.py │ │ │ ├── config.py │ │ │ ├── loss.py │ │ │ ├── lr_scheduler.py │ │ │ ├── resnet.py │ │ │ └── semantic_seg.py │ │ └── train_net.py │ ├── DensePose │ │ ├── README.md │ │ ├── apply_net.py │ │ ├── configs │ │ │ ├── Base-DensePose-RCNN-FPN.yaml │ │ │ ├── HRNet │ │ │ │ ├── densepose_rcnn_HRFPN_HRNet_w32_s1x.yaml │ │ │ │ ├── densepose_rcnn_HRFPN_HRNet_w40_s1x.yaml │ │ │ │ └── densepose_rcnn_HRFPN_HRNet_w48_s1x.yaml │ │ │ ├── cse │ │ │ │ ├── Base-DensePose-RCNN-FPN-Human.yaml │ │ │ │ ├── Base-DensePose-RCNN-FPN.yaml │ │ │ │ ├── densepose_rcnn_R_101_FPN_DL_s1x.yaml │ │ │ │ ├── densepose_rcnn_R_101_FPN_DL_soft_s1x.yaml │ │ │ │ ├── densepose_rcnn_R_101_FPN_s1x.yaml │ │ │ │ ├── densepose_rcnn_R_101_FPN_soft_s1x.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_DL_s1x.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_DL_soft_s1x.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_s1x.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_soft_animals_CA_finetune_16k.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_soft_animals_CA_finetune_4k.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_16k.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_i2m_16k.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_m2m_16k.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_soft_animals_finetune_16k.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_soft_animals_finetune_4k.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_soft_animals_finetune_maskonly_24k.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_soft_chimps_finetune_4k.yaml │ │ │ │ └── densepose_rcnn_R_50_FPN_soft_s1x.yaml │ │ │ ├── densepose_rcnn_R_101_FPN_DL_WC1M_s1x.yaml │ │ │ ├── densepose_rcnn_R_101_FPN_DL_WC1_s1x.yaml │ │ │ ├── densepose_rcnn_R_101_FPN_DL_WC2M_s1x.yaml │ │ │ ├── densepose_rcnn_R_101_FPN_DL_WC2_s1x.yaml │ │ │ ├── densepose_rcnn_R_101_FPN_DL_s1x.yaml │ │ │ ├── densepose_rcnn_R_101_FPN_WC1M_s1x.yaml │ │ │ ├── densepose_rcnn_R_101_FPN_WC1_s1x.yaml │ │ │ ├── densepose_rcnn_R_101_FPN_WC2M_s1x.yaml │ │ │ ├── densepose_rcnn_R_101_FPN_WC2_s1x.yaml │ │ │ ├── densepose_rcnn_R_101_FPN_s1x.yaml │ │ │ ├── densepose_rcnn_R_101_FPN_s1x_legacy.yaml │ │ │ ├── densepose_rcnn_R_50_FPN_DL_WC1M_s1x.yaml │ │ │ ├── densepose_rcnn_R_50_FPN_DL_WC1_s1x.yaml │ │ │ ├── densepose_rcnn_R_50_FPN_DL_WC2M_s1x.yaml │ │ │ ├── densepose_rcnn_R_50_FPN_DL_WC2_s1x.yaml │ │ │ ├── densepose_rcnn_R_50_FPN_DL_s1x.yaml │ │ │ ├── densepose_rcnn_R_50_FPN_WC1M_s1x.yaml │ │ │ ├── densepose_rcnn_R_50_FPN_WC1_s1x.yaml │ │ │ ├── densepose_rcnn_R_50_FPN_WC2M_s1x.yaml │ │ │ ├── densepose_rcnn_R_50_FPN_WC2_s1x.yaml │ │ │ ├── densepose_rcnn_R_50_FPN_s1x.yaml │ │ │ ├── densepose_rcnn_R_50_FPN_s1x_legacy.yaml │ │ │ ├── evolution │ │ │ │ ├── Base-RCNN-FPN-Atop10P_CA.yaml │ │ │ │ ├── densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA.yaml │ │ │ │ ├── densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA_B_coarsesegm.yaml │ │ │ │ ├── densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA_B_finesegm.yaml │ │ │ │ ├── densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA_B_uniform.yaml │ │ │ │ └── densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA_B_uv.yaml │ │ │ └── quick_schedules │ │ │ │ ├── cse │ │ │ │ ├── densepose_rcnn_R_50_FPN_DL_instant_test.yaml │ │ │ │ └── densepose_rcnn_R_50_FPN_soft_animals_finetune_instant_test.yaml │ │ │ │ ├── densepose_rcnn_HRFPN_HRNet_w32_instant_test.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_DL_instant_test.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_TTA_inference_acc_test.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_WC1_instant_test.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_WC2_instant_test.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_inference_acc_test.yaml │ │ │ │ ├── densepose_rcnn_R_50_FPN_instant_test.yaml │ │ │ │ └── densepose_rcnn_R_50_FPN_training_acc_test.yaml │ │ ├── densepose │ │ │ ├── __init__.py │ │ │ ├── config.py │ │ │ ├── converters │ │ │ │ ├── __init__.py │ │ │ │ ├── base.py │ │ │ │ ├── builtin.py │ │ │ │ ├── chart_output_hflip.py │ │ │ │ ├── chart_output_to_chart_result.py │ │ │ │ ├── hflip.py │ │ │ │ ├── segm_to_mask.py │ │ │ │ ├── to_chart_result.py │ │ │ │ └── to_mask.py │ │ │ ├── data │ │ │ │ ├── __init__.py │ │ │ │ ├── build.py │ │ │ │ ├── combined_loader.py │ │ │ │ ├── dataset_mapper.py │ │ │ │ ├── datasets │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── builtin.py │ │ │ │ │ ├── chimpnsee.py │ │ │ │ │ ├── coco.py │ │ │ │ │ ├── dataset_type.py │ │ │ │ │ └── lvis.py │ │ │ │ ├── image_list_dataset.py │ │ │ │ ├── inference_based_loader.py │ │ │ │ ├── meshes │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── builtin.py │ │ │ │ │ └── catalog.py │ │ │ │ ├── samplers │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── densepose_base.py │ │ │ │ │ ├── densepose_confidence_based.py │ │ │ │ │ ├── densepose_cse_base.py │ │ │ │ │ ├── densepose_cse_confidence_based.py │ │ │ │ │ ├── densepose_cse_uniform.py │ │ │ │ │ ├── densepose_uniform.py │ │ │ │ │ ├── mask_from_densepose.py │ │ │ │ │ └── prediction_to_gt.py │ │ │ │ ├── transform │ │ │ │ │ ├── __init__.py │ │ │ │ │ └── image.py │ │ │ │ ├── utils.py │ │ │ │ └── video │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── frame_selector.py │ │ │ │ │ └── video_keyframe_dataset.py │ │ │ ├── engine │ │ │ │ ├── __init__.py │ │ │ │ └── trainer.py │ │ │ ├── evaluation │ │ │ │ ├── __init__.py │ │ │ │ ├── d2_evaluator_adapter.py │ │ │ │ ├── densepose_coco_evaluation.py │ │ │ │ ├── evaluator.py │ │ │ │ ├── mesh_alignment_evaluator.py │ │ │ │ └── tensor_storage.py │ │ │ ├── modeling │ │ │ │ ├── __init__.py │ │ │ │ ├── build.py │ │ │ │ ├── confidence.py │ │ │ │ ├── cse │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── embedder.py │ │ │ │ │ ├── utils.py │ │ │ │ │ ├── vertex_direct_embedder.py │ │ │ │ │ └── vertex_feature_embedder.py │ │ │ │ ├── densepose_checkpoint.py │ │ │ │ ├── filter.py │ │ │ │ ├── hrfpn.py │ │ │ │ ├── hrnet.py │ │ │ │ ├── inference.py │ │ │ │ ├── losses │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── chart.py │ │ │ │ │ ├── chart_with_confidences.py │ │ │ │ │ ├── cse.py │ │ │ │ │ ├── cycle_pix2shape.py │ │ │ │ │ ├── cycle_shape2shape.py │ │ │ │ │ ├── embed.py │ │ │ │ │ ├── embed_utils.py │ │ │ │ │ ├── mask.py │ │ │ │ │ ├── mask_or_segm.py │ │ │ │ │ ├── registry.py │ │ │ │ │ ├── segm.py │ │ │ │ │ ├── soft_embed.py │ │ │ │ │ └── utils.py │ │ │ │ ├── predictors │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── chart.py │ │ │ │ │ ├── chart_confidence.py │ │ │ │ │ ├── chart_with_confidence.py │ │ │ │ │ ├── cse.py │ │ │ │ │ ├── cse_confidence.py │ │ │ │ │ ├── cse_with_confidence.py │ │ │ │ │ └── registry.py │ │ │ │ ├── roi_heads │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── deeplab.py │ │ │ │ │ ├── registry.py │ │ │ │ │ ├── roi_head.py │ │ │ │ │ └── v1convx.py │ │ │ │ ├── test_time_augmentation.py │ │ │ │ └── utils.py │ │ │ ├── structures │ │ │ │ ├── __init__.py │ │ │ │ ├── chart.py │ │ │ │ ├── chart_confidence.py │ │ │ │ ├── chart_result.py │ │ │ │ ├── cse.py │ │ │ │ ├── cse_confidence.py │ │ │ │ ├── data_relative.py │ │ │ │ ├── list.py │ │ │ │ ├── mesh.py │ │ │ │ └── transform_data.py │ │ │ ├── utils │ │ │ │ ├── __init__.py │ │ │ │ ├── dbhelper.py │ │ │ │ ├── logger.py │ │ │ │ └── transform.py │ │ │ └── vis │ │ │ │ ├── __init__.py │ │ │ │ ├── base.py │ │ │ │ ├── bounding_box.py │ │ │ │ ├── densepose_data_points.py │ │ │ │ ├── densepose_outputs_iuv.py │ │ │ │ ├── densepose_outputs_vertex.py │ │ │ │ ├── densepose_results.py │ │ │ │ ├── densepose_results_textures.py │ │ │ │ └── extractor.py │ │ ├── dev │ │ │ ├── README.md │ │ │ ├── run_inference_tests.sh │ │ │ └── run_instant_tests.sh │ │ ├── doc │ │ │ ├── BOOTSTRAPPING_PIPELINE.md │ │ │ ├── DENSEPOSE_CSE.md │ │ │ ├── DENSEPOSE_DATASETS.md │ │ │ ├── DENSEPOSE_IUV.md │ │ │ ├── GETTING_STARTED.md │ │ │ ├── RELEASE_2020_04.md │ │ │ ├── RELEASE_2021_03.md │ │ │ ├── RELEASE_2021_06.md │ │ │ ├── TOOL_APPLY_NET.md │ │ │ └── TOOL_QUERY_DB.md │ │ ├── query_db.py │ │ ├── setup.py │ │ ├── tests │ │ │ ├── common.py │ │ │ ├── test_chart_based_annotations_accumulator.py │ │ │ ├── test_combine_data_loader.py │ │ │ ├── test_cse_annotations_accumulator.py │ │ │ ├── test_dataset_loaded_annotations.py │ │ │ ├── test_frame_selector.py │ │ │ ├── test_image_list_dataset.py │ │ │ ├── test_image_resize_transform.py │ │ │ ├── test_model_e2e.py │ │ │ ├── test_setup.py │ │ │ ├── test_structures.py │ │ │ ├── test_tensor_storage.py │ │ │ └── test_video_keyframe_dataset.py │ │ └── train_net.py │ ├── MViTv2 │ │ ├── README.md │ │ └── configs │ │ │ ├── cascade_mask_rcnn_mvitv2_b_3x.py │ │ │ ├── cascade_mask_rcnn_mvitv2_b_in21k_3x.py │ │ │ ├── cascade_mask_rcnn_mvitv2_h_in21k_lsj_3x.py │ │ │ ├── cascade_mask_rcnn_mvitv2_l_in21k_lsj_50ep.py │ │ │ ├── cascade_mask_rcnn_mvitv2_s_3x.py │ │ │ ├── cascade_mask_rcnn_mvitv2_t_3x.py │ │ │ ├── common │ │ │ ├── coco_loader.py │ │ │ └── coco_loader_lsj.py │ │ │ └── mask_rcnn_mvitv2_t_3x.py │ ├── Panoptic-DeepLab │ │ ├── README.md │ │ ├── configs │ │ │ ├── COCO-PanopticSegmentation │ │ │ │ └── panoptic_deeplab_R_52_os16_mg124_poly_200k_bs64_crop_640_640_coco_dsconv.yaml │ │ │ └── Cityscapes-PanopticSegmentation │ │ │ │ ├── Base-PanopticDeepLab-OS16.yaml │ │ │ │ ├── panoptic_deeplab_R_52_os16_mg124_poly_90k_bs32_crop_512_1024.yaml │ │ │ │ └── panoptic_deeplab_R_52_os16_mg124_poly_90k_bs32_crop_512_1024_dsconv.yaml │ │ ├── panoptic_deeplab │ │ │ ├── __init__.py │ │ │ ├── config.py │ │ │ ├── dataset_mapper.py │ │ │ ├── panoptic_seg.py │ │ │ ├── post_processing.py │ │ │ └── target_generator.py │ │ └── train_net.py │ ├── PointRend │ │ ├── README.md │ │ ├── configs │ │ │ ├── InstanceSegmentation │ │ │ │ ├── Base-Implicit-PointRend.yaml │ │ │ │ ├── Base-PointRend-RCNN-FPN.yaml │ │ │ │ ├── implicit_pointrend_R_50_FPN_1x_coco.yaml │ │ │ │ ├── implicit_pointrend_R_50_FPN_3x_coco.yaml │ │ │ │ ├── pointrend_rcnn_R_101_FPN_3x_coco.yaml │ │ │ │ ├── pointrend_rcnn_R_50_FPN_1x_cityscapes.yaml │ │ │ │ ├── pointrend_rcnn_R_50_FPN_1x_coco.yaml │ │ │ │ ├── pointrend_rcnn_R_50_FPN_3x_coco.yaml │ │ │ │ └── pointrend_rcnn_X_101_32x8d_FPN_3x_coco.yaml │ │ │ └── SemanticSegmentation │ │ │ │ ├── Base-PointRend-Semantic-FPN.yaml │ │ │ │ └── pointrend_semantic_R_101_FPN_1x_cityscapes.yaml │ │ ├── point_rend │ │ │ ├── __init__.py │ │ │ ├── color_augmentation.py │ │ │ ├── config.py │ │ │ ├── mask_head.py │ │ │ ├── point_features.py │ │ │ ├── point_head.py │ │ │ ├── roi_heads.py │ │ │ └── semantic_seg.py │ │ └── train_net.py │ ├── PointSup │ │ ├── README.md │ │ ├── configs │ │ │ ├── implicit_pointrend_R_50_FPN_3x_point_sup_point_aug_coco.yaml │ │ │ ├── mask_rcnn_R_50_FPN_3x_point_sup_coco.yaml │ │ │ └── mask_rcnn_R_50_FPN_3x_point_sup_point_aug_coco.yaml │ │ ├── point_sup │ │ │ ├── __init__.py │ │ │ ├── config.py │ │ │ ├── dataset_mapper.py │ │ │ ├── detection_utils.py │ │ │ ├── mask_head.py │ │ │ ├── point_utils.py │ │ │ └── register_point_annotations.py │ │ ├── tools │ │ │ └── prepare_coco_point_annotations_without_masks.py │ │ └── train_net.py │ ├── README.md │ ├── Rethinking-BatchNorm │ │ ├── README.md │ │ ├── configs │ │ │ ├── mask_rcnn_BNhead.py │ │ │ ├── mask_rcnn_BNhead_batch_stats.py │ │ │ ├── mask_rcnn_BNhead_shuffle.py │ │ │ ├── mask_rcnn_SyncBNhead.py │ │ │ ├── retinanet_SyncBNhead.py │ │ │ └── retinanet_SyncBNhead_SharedTraining.py │ │ └── retinanet-eval-domain-specific.py │ ├── TensorMask │ │ ├── README.md │ │ ├── configs │ │ │ ├── Base-TensorMask.yaml │ │ │ ├── tensormask_R_50_FPN_1x.yaml │ │ │ └── tensormask_R_50_FPN_6x.yaml │ │ ├── setup.py │ │ ├── tensormask │ │ │ ├── __init__.py │ │ │ ├── arch.py │ │ │ ├── config.py │ │ │ └── layers │ │ │ │ ├── __init__.py │ │ │ │ ├── csrc │ │ │ │ ├── SwapAlign2Nat │ │ │ │ │ ├── SwapAlign2Nat.h │ │ │ │ │ └── SwapAlign2Nat_cuda.cu │ │ │ │ └── vision.cpp │ │ │ │ └── swap_align2nat.py │ │ ├── tests │ │ │ ├── __init__.py │ │ │ └── test_swap_align2nat.py │ │ └── train_net.py │ ├── TridentNet │ │ ├── README.md │ │ ├── configs │ │ │ ├── Base-TridentNet-Fast-C4.yaml │ │ │ ├── tridentnet_fast_R_101_C4_3x.yaml │ │ │ ├── tridentnet_fast_R_50_C4_1x.yaml │ │ │ └── tridentnet_fast_R_50_C4_3x.yaml │ │ ├── train_net.py │ │ └── tridentnet │ │ │ ├── __init__.py │ │ │ ├── config.py │ │ │ ├── trident_backbone.py │ │ │ ├── trident_conv.py │ │ │ ├── trident_rcnn.py │ │ │ └── trident_rpn.py │ └── ViTDet │ │ ├── README.md │ │ └── configs │ │ ├── COCO │ │ ├── cascade_mask_rcnn_mvitv2_b_in21k_100ep.py │ │ ├── cascade_mask_rcnn_mvitv2_h_in21k_36ep.py │ │ ├── cascade_mask_rcnn_mvitv2_l_in21k_50ep.py │ │ ├── cascade_mask_rcnn_swin_b_in21k_50ep.py │ │ ├── cascade_mask_rcnn_swin_l_in21k_50ep.py │ │ ├── cascade_mask_rcnn_vimdet_b_100ep.py │ │ ├── cascade_mask_rcnn_vimdet_s_100ep.py │ │ ├── cascade_mask_rcnn_vimdet_t_100ep.py │ │ ├── cascade_mask_rcnn_vimdet_t_100ep_adj1.py │ │ ├── cascade_mask_rcnn_vitdet_b_100ep.py │ │ ├── cascade_mask_rcnn_vitdet_h_75ep.py │ │ ├── cascade_mask_rcnn_vitdet_l_100ep.py │ │ ├── cascade_mask_rcnn_vitdet_s_100ep.py │ │ ├── cascade_mask_rcnn_vitdet_t_100ep.py │ │ ├── lite_cascade_mask_rcnn_vimdet_t_100ep.py │ │ ├── mask_rcnn_vimdet_b_100ep.py │ │ ├── mask_rcnn_vitdet_b_100ep.py │ │ ├── mask_rcnn_vitdet_h_75ep.py │ │ ├── mask_rcnn_vitdet_l_100ep.py │ │ └── mask_rcnn_vitdet_t_100ep.py │ │ ├── LVIS │ │ ├── cascade_mask_rcnn_mvitv2_b_in21k_100ep.py │ │ ├── cascade_mask_rcnn_mvitv2_h_in21k_50ep.py │ │ ├── cascade_mask_rcnn_mvitv2_l_in21k_50ep.py │ │ ├── cascade_mask_rcnn_swin_b_in21k_50ep.py │ │ ├── cascade_mask_rcnn_swin_l_in21k_50ep.py │ │ ├── cascade_mask_rcnn_vitdet_b_100ep.py │ │ ├── cascade_mask_rcnn_vitdet_h_100ep.py │ │ ├── cascade_mask_rcnn_vitdet_l_100ep.py │ │ ├── mask_rcnn_vitdet_b_100ep.py │ │ ├── mask_rcnn_vitdet_h_100ep.py │ │ └── mask_rcnn_vitdet_l_100ep.py │ │ └── common │ │ └── coco_loader_lsj.py ├── scripts │ ├── eval_vim_tiny_vimdet.sh │ └── ft_vim_tiny_vimdet.sh ├── setup.cfg ├── setup.py ├── tests │ ├── README.md │ ├── __init__.py │ ├── config │ │ ├── dir1 │ │ │ ├── bad_import.py │ │ │ ├── bad_import2.py │ │ │ ├── dir1_a.py │ │ │ ├── dir1_b.py │ │ │ └── load_rel.py │ │ ├── root_cfg.py │ │ ├── test_instantiate_config.py │ │ ├── test_lazy_config.py │ │ └── test_yacs_config.py │ ├── data │ │ ├── __init__.py │ │ ├── test_coco.py │ │ ├── test_coco_evaluation.py │ │ ├── test_dataset.py │ │ ├── test_detection_utils.py │ │ ├── test_rotation_transform.py │ │ ├── test_sampler.py │ │ └── test_transforms.py │ ├── export │ │ └── test_c10.py │ ├── layers │ │ ├── __init__.py │ │ ├── test_blocks.py │ │ ├── test_deformable.py │ │ ├── test_losses.py │ │ ├── test_mask_ops.py │ │ ├── test_nms.py │ │ ├── test_nms_rotated.py │ │ ├── test_roi_align.py │ │ └── test_roi_align_rotated.py │ ├── modeling │ │ ├── __init__.py │ │ ├── test_anchor_generator.py │ │ ├── test_backbone.py │ │ ├── test_box2box_transform.py │ │ ├── test_fast_rcnn.py │ │ ├── test_matcher.py │ │ ├── test_mmdet.py │ │ ├── test_model_e2e.py │ │ ├── test_roi_heads.py │ │ ├── test_roi_pooler.py │ │ └── test_rpn.py │ ├── structures │ │ ├── __init__.py │ │ ├── test_boxes.py │ │ ├── test_imagelist.py │ │ ├── test_instances.py │ │ ├── test_keypoints.py │ │ ├── test_masks.py │ │ └── test_rotated_boxes.py │ ├── test_checkpoint.py │ ├── test_engine.py │ ├── test_events.py │ ├── test_export_caffe2.py │ ├── test_export_onnx.py │ ├── test_export_torchscript.py │ ├── test_model_analysis.py │ ├── test_model_zoo.py │ ├── test_packaging.py │ ├── test_registry.py │ ├── test_scheduler.py │ ├── test_solver.py │ ├── test_visualizer.py │ ├── tracking │ │ ├── __init__.py │ │ ├── test_bbox_iou_tracker.py │ │ ├── test_hungarian_tracker.py │ │ ├── test_iou_weighted_hungarian_bbox_iou_tracker.py │ │ └── test_vanilla_hungarian_bbox_iou_tracker.py │ └── utils │ │ └── test_tensorboardx.py └── tools │ ├── README.md │ ├── __init__.py │ ├── analyze_model.py │ ├── benchmark.py │ ├── convert-torchvision-to-d2.py │ ├── deploy │ ├── CMakeLists.txt │ ├── README.md │ ├── export_model.py │ └── torchscript_mask_rcnn.cpp │ ├── lazyconfig_train_net.py │ ├── lightning_train_net.py │ ├── plain_train_net.py │ ├── train_net.py │ ├── visualize_data.py │ └── visualize_json_results.py ├── mamba-1p1p1 ├── .github │ └── workflows │ │ └── publish.yaml ├── .gitignore ├── .gitmodules ├── AUTHORS ├── LICENSE ├── README.md ├── assets │ └── selection.png ├── benchmarks │ └── benchmark_generation_mamba_simple.py ├── csrc │ └── selective_scan │ │ ├── reverse_scan.cuh │ │ ├── selective_scan.cpp │ │ ├── selective_scan.h │ │ ├── selective_scan_bwd_bf16_complex.cu │ │ ├── selective_scan_bwd_bf16_real.cu │ │ ├── selective_scan_bwd_fp16_complex.cu │ │ ├── selective_scan_bwd_fp16_real.cu │ │ ├── selective_scan_bwd_fp32_complex.cu │ │ ├── selective_scan_bwd_fp32_real.cu │ │ ├── selective_scan_bwd_kernel.cuh │ │ ├── selective_scan_common.h │ │ ├── selective_scan_fwd_bf16.cu │ │ ├── selective_scan_fwd_fp16.cu │ │ ├── selective_scan_fwd_fp32.cu │ │ ├── selective_scan_fwd_kernel.cuh │ │ ├── static_switch.h │ │ └── uninitialized_copy.cuh ├── evals │ └── lm_harness_eval.py ├── mamba_ssm │ ├── __init__.py │ ├── models │ │ ├── __init__.py │ │ ├── config_mamba.py │ │ └── mixer_seq_simple.py │ ├── modules │ │ ├── __init__.py │ │ └── mamba_simple.py │ ├── ops │ │ ├── __init__.py │ │ ├── selective_scan_interface.py │ │ └── triton │ │ │ ├── __init__.py │ │ │ ├── layer_norm.py │ │ │ └── selective_state_update.py │ └── utils │ │ ├── __init__.py │ │ ├── generation.py │ │ └── hf.py ├── setup.py └── tests │ └── ops │ ├── test_selective_scan.py │ └── triton │ └── test_selective_state_update.py ├── seg ├── README.md ├── backbone │ ├── __init__.py │ └── vim.py ├── configs │ ├── _base_ │ │ ├── datasets │ │ │ ├── ade20k.py │ │ │ ├── ade20k_1024x1024.py │ │ │ ├── ade20k_640x640.py │ │ │ └── ade20k_ms_eval.py │ │ ├── default_runtime.py │ │ ├── models │ │ │ ├── plainseg_vim.py │ │ │ ├── upernet_beit.py │ │ │ └── upernet_vim.py │ │ └── schedules │ │ │ ├── schedule_60k.py │ │ │ └── schedule_80k.py │ └── vim │ │ └── upernet │ │ ├── upernet_vim_small_24_512_slide_60k.py │ │ └── upernet_vim_tiny_24_512_slide_60k.py ├── mmcv_custom │ ├── __init__.py │ ├── apex_runner │ │ ├── __init__.py │ │ ├── apex_iter_based_runner.py │ │ ├── checkpoint.py │ │ └── optimizer.py │ ├── checkpoint.py │ ├── layer_decay_optimizer_constructor.py │ ├── resize_transform.py │ └── train_api.py ├── scripts │ ├── eval_vim_small_upernet.sh │ ├── eval_vim_tiny_upernet.sh │ ├── ft_vim_small_upernet.sh │ └── ft_vim_tiny_upernet.sh ├── seg-requirements.txt ├── test.py ├── tools │ └── analysis_tools │ │ ├── benchmark.py │ │ ├── benchmark_scripts.sh │ │ ├── deit-t-upernet.txt │ │ ├── plot_curve.ipynb │ │ └── vim-t-upernet.txt └── train.py └── vim ├── .gitignore ├── LICENSE ├── augment.py ├── datasets.py ├── engine.py ├── hubconf.py ├── losses.py ├── main.py ├── models_mamba.py ├── rope.py ├── run_with_submitit.py ├── samplers.py ├── scripts ├── ft-vim-s.sh ├── ft-vim-t.sh ├── pt-vim-s.sh └── pt-vim-t.sh ├── utils.py └── vim_requirements.txt /.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/.DS_Store -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .DS_Store 2 | causal-conv1d/causal_conv1d/__pycache__/* 3 | mamba/mamba_ssm/utils/__pycache__/* 4 | mamba/mamba_ssm/ops/triton/__pycache__/* 5 | mamba/mamba_ssm/ops/__pycache__/* 6 | mamba/mamba_ssm/modules/__pycache__/* 7 | mamba/mamba_ssm/__pycache__/* 8 | mamba/mamba_ssm/models/__pycache__/* 9 | causal-conv1d/build/ 10 | causal-conv1d/causal_conv1d.egg-info/ 11 | causal-conv1d/causal_conv1d_cuda.cpython-310-x86_64-linux-gnu.so 12 | mamba/build/ 13 | mamba/mamba_ssm.egg-info/ 14 | mamba/selective_scan_cuda.cpython-310-x86_64-linux-gnu.so 15 | reference/ 16 | causal-conv1d/ 17 | work_dirs/ 18 | __pycache__/ -------------------------------------------------------------------------------- /assets/vim_pipeline_v1.9.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/assets/vim_pipeline_v1.9.png -------------------------------------------------------------------------------- /assets/vim_teaser_v1.7.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/assets/vim_teaser_v1.7.png -------------------------------------------------------------------------------- /causal-conv1d/AUTHORS: -------------------------------------------------------------------------------- 1 | Tri Dao, tri@tridao.me 2 | -------------------------------------------------------------------------------- /causal-conv1d/causal_conv1d/__init__.py: -------------------------------------------------------------------------------- 1 | __version__ = "1.4.0" 2 | 3 | from causal_conv1d.causal_conv1d_interface import causal_conv1d_fn, causal_conv1d_update 4 | -------------------------------------------------------------------------------- /det/.circleci/import-tests.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash -e 2 | # Copyright (c) Facebook, Inc. and its affiliates. 3 | 4 | # Test that import works without building detectron2. 5 | 6 | # Check that _C is not importable 7 | python -c "from detectron2 import _C" > /dev/null 2>&1 && { 8 | echo "This test should be run without building detectron2." 9 | exit 1 10 | } 11 | 12 | # Check that other modules are still importable, even when _C is not importable 13 | python -c "from detectron2 import modeling" 14 | python -c "from detectron2 import modeling, data" 15 | python -c "from detectron2 import evaluation, export, checkpoint" 16 | python -c "from detectron2 import utils, engine" 17 | -------------------------------------------------------------------------------- /det/.flake8: -------------------------------------------------------------------------------- 1 | # This is an example .flake8 config, used when developing *Black* itself. 2 | # Keep in sync with setup.cfg which is used for source packages. 3 | 4 | [flake8] 5 | ignore = W503, E203, E221, C901, C408, E741, C407, B017, F811, C101, EXE001, EXE002 6 | max-line-length = 100 7 | max-complexity = 18 8 | select = B,C,E,F,W,T4,B9 9 | exclude = build 10 | per-file-ignores = 11 | **/__init__.py:F401,F403,E402 12 | **/configs/**.py:F401,E402 13 | configs/**.py:F401,E402 14 | **/tests/config/**.py:F401,E402 15 | tests/config/**.py:F401,E402 16 | -------------------------------------------------------------------------------- /det/.gitignore: -------------------------------------------------------------------------------- 1 | # output dir 2 | output 3 | instant_test_output 4 | inference_test_output 5 | 6 | 7 | *.png 8 | *.json 9 | *.diff 10 | *.jpg 11 | !/projects/DensePose/doc/images/*.jpg 12 | 13 | # compilation and distribution 14 | __pycache__ 15 | _ext 16 | *.pyc 17 | *.pyd 18 | *.so 19 | *.dll 20 | *.egg-info/ 21 | build/ 22 | dist/ 23 | wheels/ 24 | released_ckpt/ 25 | work_dirs/ 26 | 27 | # pytorch/python/numpy formats 28 | *.pth 29 | *.pkl 30 | *.npy 31 | *.ts 32 | model_ts*.txt 33 | 34 | # ipython/jupyter notebooks 35 | *.ipynb 36 | **/.ipynb_checkpoints/ 37 | 38 | # Editor temporaries 39 | *.swn 40 | *.swo 41 | *.swp 42 | *~ 43 | 44 | # editor settings 45 | .idea 46 | .vscode 47 | _darcs 48 | 49 | # project dirs 50 | /detectron2/model_zoo/configs 51 | /datasets/* 52 | !/datasets/*.* 53 | /projects/*/datasets 54 | /models 55 | /snippet 56 | -------------------------------------------------------------------------------- /det/configs/Base-RCNN-C4.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | RPN: 4 | PRE_NMS_TOPK_TEST: 6000 5 | POST_NMS_TOPK_TEST: 1000 6 | ROI_HEADS: 7 | NAME: "Res5ROIHeads" 8 | DATASETS: 9 | TRAIN: ("coco_2017_train",) 10 | TEST: ("coco_2017_val",) 11 | SOLVER: 12 | IMS_PER_BATCH: 16 13 | BASE_LR: 0.02 14 | STEPS: (60000, 80000) 15 | MAX_ITER: 90000 16 | INPUT: 17 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 18 | VERSION: 2 19 | -------------------------------------------------------------------------------- /det/configs/Base-RCNN-DilatedC5.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | RESNETS: 4 | OUT_FEATURES: ["res5"] 5 | RES5_DILATION: 2 6 | RPN: 7 | IN_FEATURES: ["res5"] 8 | PRE_NMS_TOPK_TEST: 6000 9 | POST_NMS_TOPK_TEST: 1000 10 | ROI_HEADS: 11 | NAME: "StandardROIHeads" 12 | IN_FEATURES: ["res5"] 13 | ROI_BOX_HEAD: 14 | NAME: "FastRCNNConvFCHead" 15 | NUM_FC: 2 16 | POOLER_RESOLUTION: 7 17 | ROI_MASK_HEAD: 18 | NAME: "MaskRCNNConvUpsampleHead" 19 | NUM_CONV: 4 20 | POOLER_RESOLUTION: 14 21 | DATASETS: 22 | TRAIN: ("coco_2017_train",) 23 | TEST: ("coco_2017_val",) 24 | SOLVER: 25 | IMS_PER_BATCH: 16 26 | BASE_LR: 0.02 27 | STEPS: (60000, 80000) 28 | MAX_ITER: 90000 29 | INPUT: 30 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 31 | VERSION: 2 32 | -------------------------------------------------------------------------------- /det/configs/Base-RetinaNet.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "RetinaNet" 3 | BACKBONE: 4 | NAME: "build_retinanet_resnet_fpn_backbone" 5 | RESNETS: 6 | OUT_FEATURES: ["res3", "res4", "res5"] 7 | ANCHOR_GENERATOR: 8 | SIZES: !!python/object/apply:eval ["[[x, x * 2**(1.0/3), x * 2**(2.0/3) ] for x in [32, 64, 128, 256, 512 ]]"] 9 | FPN: 10 | IN_FEATURES: ["res3", "res4", "res5"] 11 | RETINANET: 12 | IOU_THRESHOLDS: [0.4, 0.5] 13 | IOU_LABELS: [0, -1, 1] 14 | SMOOTH_L1_LOSS_BETA: 0.0 15 | DATASETS: 16 | TRAIN: ("coco_2017_train",) 17 | TEST: ("coco_2017_val",) 18 | SOLVER: 19 | IMS_PER_BATCH: 16 20 | BASE_LR: 0.01 # Note that RetinaNet uses a different default learning rate 21 | STEPS: (60000, 80000) 22 | MAX_ITER: 90000 23 | INPUT: 24 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 25 | VERSION: 2 26 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: False 5 | LOAD_PROPOSALS: True 6 | RESNETS: 7 | DEPTH: 50 8 | PROPOSAL_GENERATOR: 9 | NAME: "PrecomputedProposals" 10 | DATASETS: 11 | TRAIN: ("coco_2017_train",) 12 | PROPOSAL_FILES_TRAIN: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_train_box_proposals_21bc3a.pkl", ) 13 | TEST: ("coco_2017_val",) 14 | PROPOSAL_FILES_TEST: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_val_box_proposals_ee0dad.pkl", ) 15 | DATALOADER: 16 | # proposals are part of the dataset_dicts, and take a lot of RAM 17 | NUM_WORKERS: 2 18 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/faster_rcnn_R_101_C4_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-C4.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 101 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/faster_rcnn_R_101_DC5_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-DilatedC5.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 101 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/faster_rcnn_R_101_FPN_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 101 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/faster_rcnn_R_50_C4_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-C4.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 50 7 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/faster_rcnn_R_50_C4_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-C4.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 50 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/faster_rcnn_R_50_DC5_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-DilatedC5.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 50 7 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/faster_rcnn_R_50_DC5_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-DilatedC5.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 50 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/faster_rcnn_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 50 7 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 50 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | MASK_ON: False 4 | WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl" 5 | PIXEL_STD: [57.375, 57.120, 58.395] 6 | RESNETS: 7 | STRIDE_IN_1X1: False # this is a C2 model 8 | NUM_GROUPS: 32 9 | WIDTH_PER_GROUP: 8 10 | DEPTH: 101 11 | SOLVER: 12 | STEPS: (210000, 250000) 13 | MAX_ITER: 270000 14 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/fcos_R_50_FPN_1x.py: -------------------------------------------------------------------------------- 1 | from ..common.optim import SGD as optimizer 2 | from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier 3 | from ..common.data.coco import dataloader 4 | from ..common.models.fcos import model 5 | from ..common.train import train 6 | 7 | dataloader.train.mapper.use_instance_mask = False 8 | optimizer.lr = 0.01 9 | 10 | model.backbone.bottom_up.freeze_at = 2 11 | train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 12 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/retinanet_R_101_FPN_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RetinaNet.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | SOLVER: 7 | STEPS: (210000, 250000) 8 | MAX_ITER: 270000 9 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/retinanet_R_50_FPN_1x.py: -------------------------------------------------------------------------------- 1 | from ..common.optim import SGD as optimizer 2 | from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier 3 | from ..common.data.coco import dataloader 4 | from ..common.models.retinanet import model 5 | from ..common.train import train 6 | 7 | dataloader.train.mapper.use_instance_mask = False 8 | model.backbone.bottom_up.freeze_at = 2 9 | optimizer.lr = 0.01 10 | 11 | train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 12 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/retinanet_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RetinaNet.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/retinanet_R_50_FPN_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RetinaNet.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | SOLVER: 7 | STEPS: (210000, 250000) 8 | MAX_ITER: 270000 9 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/rpn_R_50_C4_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-C4.yaml" 2 | MODEL: 3 | META_ARCHITECTURE: "ProposalNetwork" 4 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 5 | MASK_ON: False 6 | RESNETS: 7 | DEPTH: 50 8 | RPN: 9 | PRE_NMS_TOPK_TEST: 12000 10 | POST_NMS_TOPK_TEST: 2000 11 | -------------------------------------------------------------------------------- /det/configs/COCO-Detection/rpn_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | META_ARCHITECTURE: "ProposalNetwork" 4 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 5 | MASK_ON: False 6 | RESNETS: 7 | DEPTH: 50 8 | RPN: 9 | POST_NMS_TOPK_TEST: 2000 10 | -------------------------------------------------------------------------------- /det/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-C4.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 101 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | -------------------------------------------------------------------------------- /det/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_DC5_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-DilatedC5.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 101 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | -------------------------------------------------------------------------------- /det/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 101 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | -------------------------------------------------------------------------------- /det/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.py: -------------------------------------------------------------------------------- 1 | from ..common.train import train 2 | from ..common.optim import SGD as optimizer 3 | from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier 4 | from ..common.data.coco import dataloader 5 | from ..common.models.mask_rcnn_c4 import model 6 | 7 | model.backbone.freeze_at = 2 8 | train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 9 | -------------------------------------------------------------------------------- /det/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-C4.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | -------------------------------------------------------------------------------- /det/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-C4.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | -------------------------------------------------------------------------------- /det/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-DilatedC5.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | -------------------------------------------------------------------------------- /det/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-DilatedC5.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | -------------------------------------------------------------------------------- /det/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.py: -------------------------------------------------------------------------------- 1 | from ..common.optim import SGD as optimizer 2 | from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier 3 | from ..common.data.coco import dataloader 4 | from ..common.models.mask_rcnn_fpn import model 5 | from ..common.train import train 6 | 7 | model.backbone.bottom_up.freeze_at = 2 8 | train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 9 | -------------------------------------------------------------------------------- /det/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | -------------------------------------------------------------------------------- /det/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x_giou.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | RPN: 8 | BBOX_REG_LOSS_TYPE: "giou" 9 | BBOX_REG_LOSS_WEIGHT: 2.0 10 | ROI_BOX_HEAD: 11 | BBOX_REG_LOSS_TYPE: "giou" 12 | BBOX_REG_LOSS_WEIGHT: 10.0 13 | -------------------------------------------------------------------------------- /det/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | -------------------------------------------------------------------------------- /det/configs/COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | MASK_ON: True 4 | WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl" 5 | PIXEL_STD: [57.375, 57.120, 58.395] 6 | RESNETS: 7 | STRIDE_IN_1X1: False # this is a C2 model 8 | NUM_GROUPS: 32 9 | WIDTH_PER_GROUP: 8 10 | DEPTH: 101 11 | SOLVER: 12 | STEPS: (210000, 250000) 13 | MAX_ITER: 270000 14 | -------------------------------------------------------------------------------- /det/configs/COCO-Keypoints/Base-Keypoint-RCNN-FPN.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | KEYPOINT_ON: True 4 | ROI_HEADS: 5 | NUM_CLASSES: 1 6 | ROI_BOX_HEAD: 7 | SMOOTH_L1_BETA: 0.5 # Keypoint AP degrades (though box AP improves) when using plain L1 loss 8 | RPN: 9 | # Detectron1 uses 2000 proposals per-batch, but this option is per-image in detectron2. 10 | # 1000 proposals per-image is found to hurt box AP. 11 | # Therefore we increase it to 1500 per-image. 12 | POST_NMS_TOPK_TRAIN: 1500 13 | DATASETS: 14 | TRAIN: ("keypoints_coco_2017_train",) 15 | TEST: ("keypoints_coco_2017_val",) 16 | -------------------------------------------------------------------------------- /det/configs/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-Keypoint-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | SOLVER: 7 | STEPS: (210000, 250000) 8 | MAX_ITER: 270000 9 | -------------------------------------------------------------------------------- /det/configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x.py: -------------------------------------------------------------------------------- 1 | from ..common.optim import SGD as optimizer 2 | from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier 3 | from ..common.data.coco_keypoint import dataloader 4 | from ..common.models.keypoint_rcnn_fpn import model 5 | from ..common.train import train 6 | 7 | model.backbone.bottom_up.freeze_at = 2 8 | train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 9 | -------------------------------------------------------------------------------- /det/configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-Keypoint-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | -------------------------------------------------------------------------------- /det/configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-Keypoint-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | SOLVER: 7 | STEPS: (210000, 250000) 8 | MAX_ITER: 270000 9 | -------------------------------------------------------------------------------- /det/configs/COCO-Keypoints/keypoint_rcnn_X_101_32x8d_FPN_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-Keypoint-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl" 4 | PIXEL_STD: [57.375, 57.120, 58.395] 5 | RESNETS: 6 | STRIDE_IN_1X1: False # this is a C2 model 7 | NUM_GROUPS: 32 8 | WIDTH_PER_GROUP: 8 9 | DEPTH: 101 10 | SOLVER: 11 | STEPS: (210000, 250000) 12 | MAX_ITER: 270000 13 | -------------------------------------------------------------------------------- /det/configs/COCO-PanopticSegmentation/Base-Panoptic-FPN.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | META_ARCHITECTURE: "PanopticFPN" 4 | MASK_ON: True 5 | SEM_SEG_HEAD: 6 | LOSS_WEIGHT: 0.5 7 | DATASETS: 8 | TRAIN: ("coco_2017_train_panoptic_separated",) 9 | TEST: ("coco_2017_val_panoptic_separated",) 10 | DATALOADER: 11 | FILTER_EMPTY_ANNOTATIONS: False 12 | -------------------------------------------------------------------------------- /det/configs/COCO-PanopticSegmentation/panoptic_fpn_R_101_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-Panoptic-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | SOLVER: 7 | STEPS: (210000, 250000) 8 | MAX_ITER: 270000 9 | -------------------------------------------------------------------------------- /det/configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x.py: -------------------------------------------------------------------------------- 1 | from ..common.optim import SGD as optimizer 2 | from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier 3 | from ..common.data.coco_panoptic_separated import dataloader 4 | from ..common.models.panoptic_fpn import model 5 | from ..common.train import train 6 | 7 | model.backbone.bottom_up.freeze_at = 2 8 | train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 9 | -------------------------------------------------------------------------------- /det/configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-Panoptic-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | -------------------------------------------------------------------------------- /det/configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-Panoptic-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | SOLVER: 7 | STEPS: (210000, 250000) 8 | MAX_ITER: 270000 9 | -------------------------------------------------------------------------------- /det/configs/Detectron1-Comparisons/faster_rcnn_R_50_FPN_noaug_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 50 7 | # Detectron1 uses smooth L1 loss with some magic beta values. 8 | # The defaults are changed to L1 loss in Detectron2. 9 | RPN: 10 | SMOOTH_L1_BETA: 0.1111 11 | ROI_BOX_HEAD: 12 | SMOOTH_L1_BETA: 1.0 13 | POOLER_SAMPLING_RATIO: 2 14 | POOLER_TYPE: "ROIAlign" 15 | INPUT: 16 | # no scale augmentation 17 | MIN_SIZE_TRAIN: (800, ) 18 | -------------------------------------------------------------------------------- /det/configs/Detectron1-Comparisons/mask_rcnn_R_50_FPN_noaug_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | # Detectron1 uses smooth L1 loss with some magic beta values. 8 | # The defaults are changed to L1 loss in Detectron2. 9 | RPN: 10 | SMOOTH_L1_BETA: 0.1111 11 | ROI_BOX_HEAD: 12 | SMOOTH_L1_BETA: 1.0 13 | POOLER_SAMPLING_RATIO: 2 14 | POOLER_TYPE: "ROIAlign" 15 | ROI_MASK_HEAD: 16 | POOLER_SAMPLING_RATIO: 2 17 | POOLER_TYPE: "ROIAlign" 18 | INPUT: 19 | # no scale augmentation 20 | MIN_SIZE_TRAIN: (800, ) 21 | -------------------------------------------------------------------------------- /det/configs/LVISv0.5-InstanceSegmentation/mask_rcnn_R_101_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 101 7 | ROI_HEADS: 8 | NUM_CLASSES: 1230 9 | SCORE_THRESH_TEST: 0.0001 10 | INPUT: 11 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 12 | DATASETS: 13 | TRAIN: ("lvis_v0.5_train",) 14 | TEST: ("lvis_v0.5_val",) 15 | TEST: 16 | DETECTIONS_PER_IMAGE: 300 # LVIS allows up to 300 17 | DATALOADER: 18 | SAMPLER_TRAIN: "RepeatFactorTrainingSampler" 19 | REPEAT_THRESHOLD: 0.001 20 | -------------------------------------------------------------------------------- /det/configs/LVISv0.5-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | ROI_HEADS: 8 | NUM_CLASSES: 1230 9 | SCORE_THRESH_TEST: 0.0001 10 | INPUT: 11 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 12 | DATASETS: 13 | TRAIN: ("lvis_v0.5_train",) 14 | TEST: ("lvis_v0.5_val",) 15 | TEST: 16 | DETECTIONS_PER_IMAGE: 300 # LVIS allows up to 300 17 | DATALOADER: 18 | SAMPLER_TRAIN: "RepeatFactorTrainingSampler" 19 | REPEAT_THRESHOLD: 0.001 20 | -------------------------------------------------------------------------------- /det/configs/LVISv0.5-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl" 4 | PIXEL_STD: [57.375, 57.120, 58.395] 5 | MASK_ON: True 6 | RESNETS: 7 | STRIDE_IN_1X1: False # this is a C2 model 8 | NUM_GROUPS: 32 9 | WIDTH_PER_GROUP: 8 10 | DEPTH: 101 11 | ROI_HEADS: 12 | NUM_CLASSES: 1230 13 | SCORE_THRESH_TEST: 0.0001 14 | INPUT: 15 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 16 | DATASETS: 17 | TRAIN: ("lvis_v0.5_train",) 18 | TEST: ("lvis_v0.5_val",) 19 | TEST: 20 | DETECTIONS_PER_IMAGE: 300 # LVIS allows up to 300 21 | DATALOADER: 22 | SAMPLER_TRAIN: "RepeatFactorTrainingSampler" 23 | REPEAT_THRESHOLD: 0.001 24 | -------------------------------------------------------------------------------- /det/configs/LVISv1-InstanceSegmentation/mask_rcnn_R_101_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 101 7 | ROI_HEADS: 8 | NUM_CLASSES: 1203 9 | SCORE_THRESH_TEST: 0.0001 10 | INPUT: 11 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 12 | DATASETS: 13 | TRAIN: ("lvis_v1_train",) 14 | TEST: ("lvis_v1_val",) 15 | TEST: 16 | DETECTIONS_PER_IMAGE: 300 # LVIS allows up to 300 17 | SOLVER: 18 | STEPS: (120000, 160000) 19 | MAX_ITER: 180000 # 180000 * 16 / 100000 ~ 28.8 epochs 20 | DATALOADER: 21 | SAMPLER_TRAIN: "RepeatFactorTrainingSampler" 22 | REPEAT_THRESHOLD: 0.001 23 | -------------------------------------------------------------------------------- /det/configs/LVISv1-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | ROI_HEADS: 8 | NUM_CLASSES: 1203 9 | SCORE_THRESH_TEST: 0.0001 10 | INPUT: 11 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 12 | DATASETS: 13 | TRAIN: ("lvis_v1_train",) 14 | TEST: ("lvis_v1_val",) 15 | TEST: 16 | DETECTIONS_PER_IMAGE: 300 # LVIS allows up to 300 17 | SOLVER: 18 | STEPS: (120000, 160000) 19 | MAX_ITER: 180000 # 180000 * 16 / 100000 ~ 28.8 epochs 20 | DATALOADER: 21 | SAMPLER_TRAIN: "RepeatFactorTrainingSampler" 22 | REPEAT_THRESHOLD: 0.001 23 | -------------------------------------------------------------------------------- /det/configs/LVISv1-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl" 4 | PIXEL_STD: [57.375, 57.120, 58.395] 5 | MASK_ON: True 6 | RESNETS: 7 | STRIDE_IN_1X1: False # this is a C2 model 8 | NUM_GROUPS: 32 9 | WIDTH_PER_GROUP: 8 10 | DEPTH: 101 11 | ROI_HEADS: 12 | NUM_CLASSES: 1203 13 | SCORE_THRESH_TEST: 0.0001 14 | INPUT: 15 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 16 | DATASETS: 17 | TRAIN: ("lvis_v1_train",) 18 | TEST: ("lvis_v1_val",) 19 | SOLVER: 20 | STEPS: (120000, 160000) 21 | MAX_ITER: 180000 # 180000 * 16 / 100000 ~ 28.8 epochs 22 | TEST: 23 | DETECTIONS_PER_IMAGE: 300 # LVIS allows up to 300 24 | DATALOADER: 25 | SAMPLER_TRAIN: "RepeatFactorTrainingSampler" 26 | REPEAT_THRESHOLD: 0.001 27 | -------------------------------------------------------------------------------- /det/configs/Misc/cascade_mask_rcnn_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | ROI_HEADS: 8 | NAME: CascadeROIHeads 9 | ROI_BOX_HEAD: 10 | CLS_AGNOSTIC_BBOX_REG: True 11 | RPN: 12 | POST_NMS_TOPK_TRAIN: 2000 13 | -------------------------------------------------------------------------------- /det/configs/Misc/cascade_mask_rcnn_R_50_FPN_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | ROI_HEADS: 8 | NAME: CascadeROIHeads 9 | ROI_BOX_HEAD: 10 | CLS_AGNOSTIC_BBOX_REG: True 11 | RPN: 12 | POST_NMS_TOPK_TRAIN: 2000 13 | SOLVER: 14 | STEPS: (210000, 250000) 15 | MAX_ITER: 270000 16 | -------------------------------------------------------------------------------- /det/configs/Misc/cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | MASK_ON: True 4 | WEIGHTS: "catalog://ImageNetPretrained/FAIR/X-152-32x8d-IN5k" 5 | RESNETS: 6 | STRIDE_IN_1X1: False # this is a C2 model 7 | NUM_GROUPS: 32 8 | WIDTH_PER_GROUP: 8 9 | DEPTH: 152 10 | DEFORM_ON_PER_STAGE: [False, True, True, True] 11 | ROI_HEADS: 12 | NAME: "CascadeROIHeads" 13 | ROI_BOX_HEAD: 14 | NAME: "FastRCNNConvFCHead" 15 | NUM_CONV: 4 16 | NUM_FC: 1 17 | NORM: "GN" 18 | CLS_AGNOSTIC_BBOX_REG: True 19 | ROI_MASK_HEAD: 20 | NUM_CONV: 8 21 | NORM: "GN" 22 | RPN: 23 | POST_NMS_TOPK_TRAIN: 2000 24 | SOLVER: 25 | IMS_PER_BATCH: 128 26 | STEPS: (35000, 45000) 27 | MAX_ITER: 50000 28 | BASE_LR: 0.16 29 | INPUT: 30 | MIN_SIZE_TRAIN: (640, 864) 31 | MIN_SIZE_TRAIN_SAMPLING: "range" 32 | MAX_SIZE_TRAIN: 1440 33 | CROP: 34 | ENABLED: True 35 | TEST: 36 | EVAL_PERIOD: 2500 37 | -------------------------------------------------------------------------------- /det/configs/Misc/mask_rcnn_R_50_FPN_1x_cls_agnostic.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | ROI_BOX_HEAD: 8 | CLS_AGNOSTIC_BBOX_REG: True 9 | ROI_MASK_HEAD: 10 | CLS_AGNOSTIC_MASK: True 11 | -------------------------------------------------------------------------------- /det/configs/Misc/mask_rcnn_R_50_FPN_1x_dconv_c3-c5.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | DEFORM_ON_PER_STAGE: [False, True, True, True] # on Res3,Res4,Res5 8 | DEFORM_MODULATED: False 9 | -------------------------------------------------------------------------------- /det/configs/Misc/mask_rcnn_R_50_FPN_3x_dconv_c3-c5.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | DEFORM_ON_PER_STAGE: [False, True, True, True] # on Res3,Res4,Res5 8 | DEFORM_MODULATED: False 9 | SOLVER: 10 | STEPS: (210000, 250000) 11 | MAX_ITER: 270000 12 | -------------------------------------------------------------------------------- /det/configs/Misc/mask_rcnn_R_50_FPN_3x_gn.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "catalog://ImageNetPretrained/FAIR/R-50-GN" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | NORM: "GN" 8 | STRIDE_IN_1X1: False 9 | FPN: 10 | NORM: "GN" 11 | ROI_BOX_HEAD: 12 | NAME: "FastRCNNConvFCHead" 13 | NUM_CONV: 4 14 | NUM_FC: 1 15 | NORM: "GN" 16 | ROI_MASK_HEAD: 17 | NORM: "GN" 18 | SOLVER: 19 | # 3x schedule 20 | STEPS: (210000, 250000) 21 | MAX_ITER: 270000 22 | -------------------------------------------------------------------------------- /det/configs/Misc/mask_rcnn_R_50_FPN_3x_syncbn.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | NORM: "SyncBN" 8 | STRIDE_IN_1X1: True 9 | FPN: 10 | NORM: "SyncBN" 11 | ROI_BOX_HEAD: 12 | NAME: "FastRCNNConvFCHead" 13 | NUM_CONV: 4 14 | NUM_FC: 1 15 | NORM: "SyncBN" 16 | ROI_MASK_HEAD: 17 | NORM: "SyncBN" 18 | SOLVER: 19 | # 3x schedule 20 | STEPS: (210000, 250000) 21 | MAX_ITER: 270000 22 | TEST: 23 | PRECISE_BN: 24 | ENABLED: True 25 | -------------------------------------------------------------------------------- /det/configs/Misc/panoptic_fpn_R_101_dconv_cascade_gn_3x.yaml: -------------------------------------------------------------------------------- 1 | # A large PanopticFPN for demo purposes. 2 | # Use GN on backbone to support semantic seg. 3 | # Use Cascade + Deform Conv to improve localization. 4 | _BASE_: "../COCO-PanopticSegmentation/Base-Panoptic-FPN.yaml" 5 | MODEL: 6 | WEIGHTS: "catalog://ImageNetPretrained/FAIR/R-101-GN" 7 | RESNETS: 8 | DEPTH: 101 9 | NORM: "GN" 10 | DEFORM_ON_PER_STAGE: [False, True, True, True] 11 | STRIDE_IN_1X1: False 12 | FPN: 13 | NORM: "GN" 14 | ROI_HEADS: 15 | NAME: CascadeROIHeads 16 | ROI_BOX_HEAD: 17 | CLS_AGNOSTIC_BBOX_REG: True 18 | ROI_MASK_HEAD: 19 | NORM: "GN" 20 | RPN: 21 | POST_NMS_TOPK_TRAIN: 2000 22 | SOLVER: 23 | STEPS: (105000, 125000) 24 | MAX_ITER: 135000 25 | IMS_PER_BATCH: 32 26 | BASE_LR: 0.04 27 | -------------------------------------------------------------------------------- /det/configs/Misc/scratch_mask_rcnn_R_50_FPN_3x_gn.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "mask_rcnn_R_50_FPN_3x_gn.yaml" 2 | MODEL: 3 | # Train from random initialization. 4 | WEIGHTS: "" 5 | # It makes sense to divide by STD when training from scratch 6 | # But it seems to make no difference on the results and C2's models didn't do this. 7 | # So we keep things consistent with C2. 8 | # PIXEL_STD: [57.375, 57.12, 58.395] 9 | MASK_ON: True 10 | BACKBONE: 11 | FREEZE_AT: 0 12 | # NOTE: Please refer to Rethinking ImageNet Pre-training https://arxiv.org/abs/1811.08883 13 | # to learn what you need for training from scratch. 14 | -------------------------------------------------------------------------------- /det/configs/Misc/scratch_mask_rcnn_R_50_FPN_9x_gn.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "mask_rcnn_R_50_FPN_3x_gn.yaml" 2 | MODEL: 3 | PIXEL_STD: [57.375, 57.12, 58.395] 4 | WEIGHTS: "" 5 | MASK_ON: True 6 | RESNETS: 7 | STRIDE_IN_1X1: False 8 | BACKBONE: 9 | FREEZE_AT: 0 10 | SOLVER: 11 | # 9x schedule 12 | IMS_PER_BATCH: 64 # 4x the standard 13 | STEPS: (187500, 197500) # last 60/4==15k and last 20/4==5k 14 | MAX_ITER: 202500 # 90k * 9 / 4 15 | BASE_LR: 0.08 16 | TEST: 17 | EVAL_PERIOD: 2500 18 | # NOTE: Please refer to Rethinking ImageNet Pre-training https://arxiv.org/abs/1811.08883 19 | # to learn what you need for training from scratch. 20 | -------------------------------------------------------------------------------- /det/configs/Misc/scratch_mask_rcnn_R_50_FPN_9x_syncbn.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "mask_rcnn_R_50_FPN_3x_syncbn.yaml" 2 | MODEL: 3 | PIXEL_STD: [57.375, 57.12, 58.395] 4 | WEIGHTS: "" 5 | MASK_ON: True 6 | RESNETS: 7 | STRIDE_IN_1X1: False 8 | BACKBONE: 9 | FREEZE_AT: 0 10 | SOLVER: 11 | # 9x schedule 12 | IMS_PER_BATCH: 64 # 4x the standard 13 | STEPS: (187500, 197500) # last 60/4==15k and last 20/4==5k 14 | MAX_ITER: 202500 # 90k * 9 / 4 15 | BASE_LR: 0.08 16 | TEST: 17 | EVAL_PERIOD: 2500 18 | # NOTE: Please refer to Rethinking ImageNet Pre-training https://arxiv.org/abs/1811.08883 19 | # to learn what you need for training from scratch. 20 | -------------------------------------------------------------------------------- /det/configs/Misc/semantic_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | META_ARCHITECTURE: "SemanticSegmentor" 4 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 5 | RESNETS: 6 | DEPTH: 50 7 | DATASETS: 8 | TRAIN: ("coco_2017_train_panoptic_stuffonly",) 9 | TEST: ("coco_2017_val_panoptic_stuffonly",) 10 | INPUT: 11 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 12 | -------------------------------------------------------------------------------- /det/configs/PascalVOC-Detection/faster_rcnn_R_50_C4.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-C4.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 50 7 | ROI_HEADS: 8 | NUM_CLASSES: 20 9 | INPUT: 10 | MIN_SIZE_TRAIN: (480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800) 11 | MIN_SIZE_TEST: 800 12 | DATASETS: 13 | TRAIN: ('voc_2007_trainval', 'voc_2012_trainval') 14 | TEST: ('voc_2007_test',) 15 | SOLVER: 16 | STEPS: (12000, 16000) 17 | MAX_ITER: 18000 # 17.4 epochs 18 | WARMUP_ITERS: 100 19 | -------------------------------------------------------------------------------- /det/configs/PascalVOC-Detection/faster_rcnn_R_50_FPN.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 50 7 | ROI_HEADS: 8 | NUM_CLASSES: 20 9 | INPUT: 10 | MIN_SIZE_TRAIN: (480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800) 11 | MIN_SIZE_TEST: 800 12 | DATASETS: 13 | TRAIN: ('voc_2007_trainval', 'voc_2012_trainval') 14 | TEST: ('voc_2007_test',) 15 | SOLVER: 16 | STEPS: (12000, 16000) 17 | MAX_ITER: 18000 # 17.4 epochs 18 | WARMUP_ITERS: 100 19 | -------------------------------------------------------------------------------- /det/configs/common/README.md: -------------------------------------------------------------------------------- 1 | This directory provides definitions for a few common models, dataloaders, scheduler, 2 | and optimizers that are often used in training. 3 | The definition of these objects are provided in the form of lazy instantiation: 4 | their arguments can be edited by users before constructing the objects. 5 | 6 | They can be imported, or loaded by `model_zoo.get_config` API in users' own configs. 7 | -------------------------------------------------------------------------------- /det/configs/common/data/coco_keypoint.py: -------------------------------------------------------------------------------- 1 | from detectron2.data.detection_utils import create_keypoint_hflip_indices 2 | 3 | from .coco import dataloader 4 | 5 | dataloader.train.dataset.min_keypoints = 1 6 | dataloader.train.dataset.names = "keypoints_coco_2017_train" 7 | dataloader.test.dataset.names = "keypoints_coco_2017_val" 8 | 9 | dataloader.train.mapper.update( 10 | use_instance_mask=False, 11 | use_keypoint=True, 12 | keypoint_hflip_indices=create_keypoint_hflip_indices(dataloader.train.dataset.names), 13 | ) 14 | -------------------------------------------------------------------------------- /det/configs/common/data/coco_panoptic_separated.py: -------------------------------------------------------------------------------- 1 | from detectron2.config import LazyCall as L 2 | from detectron2.evaluation import ( 3 | COCOEvaluator, 4 | COCOPanopticEvaluator, 5 | DatasetEvaluators, 6 | SemSegEvaluator, 7 | ) 8 | 9 | from .coco import dataloader 10 | 11 | dataloader.train.dataset.names = "coco_2017_train_panoptic_separated" 12 | dataloader.train.dataset.filter_empty = False 13 | dataloader.test.dataset.names = "coco_2017_val_panoptic_separated" 14 | 15 | 16 | dataloader.evaluator = [ 17 | L(COCOEvaluator)( 18 | dataset_name="${...test.dataset.names}", 19 | ), 20 | L(SemSegEvaluator)( 21 | dataset_name="${...test.dataset.names}", 22 | ), 23 | L(COCOPanopticEvaluator)( 24 | dataset_name="${...test.dataset.names}", 25 | ), 26 | ] 27 | -------------------------------------------------------------------------------- /det/configs/common/data/constants.py: -------------------------------------------------------------------------------- 1 | constants = dict( 2 | imagenet_rgb256_mean=[123.675, 116.28, 103.53], 3 | imagenet_rgb256_std=[58.395, 57.12, 57.375], 4 | imagenet_bgr256_mean=[103.530, 116.280, 123.675], 5 | # When using pre-trained models in Detectron1 or any MSRA models, 6 | # std has been absorbed into its conv1 weights, so the std needs to be set 1. 7 | # Otherwise, you can use [57.375, 57.120, 58.395] (ImageNet std) 8 | imagenet_bgr256_std=[1.0, 1.0, 1.0], 9 | ) 10 | -------------------------------------------------------------------------------- /det/configs/common/models/fcos.py: -------------------------------------------------------------------------------- 1 | from detectron2.modeling.meta_arch.fcos import FCOS, FCOSHead 2 | 3 | from .retinanet import model 4 | 5 | model._target_ = FCOS 6 | 7 | del model.anchor_generator 8 | del model.box2box_transform 9 | del model.anchor_matcher 10 | del model.input_format 11 | 12 | # Use P5 instead of C5 to compute P6/P7 13 | # (Sec 2.2 of https://arxiv.org/abs/2006.09214) 14 | model.backbone.top_block.in_feature = "p5" 15 | model.backbone.top_block.in_channels = 256 16 | 17 | # New score threshold determined based on sqrt(cls_score * centerness) 18 | model.test_score_thresh = 0.2 19 | model.test_nms_thresh = 0.6 20 | 21 | model.head._target_ = FCOSHead 22 | del model.head.num_anchors 23 | model.head.norm = "GN" 24 | -------------------------------------------------------------------------------- /det/configs/common/models/panoptic_fpn.py: -------------------------------------------------------------------------------- 1 | from detectron2.config import LazyCall as L 2 | from detectron2.layers import ShapeSpec 3 | from detectron2.modeling import PanopticFPN 4 | from detectron2.modeling.meta_arch.semantic_seg import SemSegFPNHead 5 | 6 | from .mask_rcnn_fpn import model 7 | 8 | model._target_ = PanopticFPN 9 | model.sem_seg_head = L(SemSegFPNHead)( 10 | input_shape={ 11 | f: L(ShapeSpec)(stride=s, channels="${....backbone.out_channels}") 12 | for f, s in zip(["p2", "p3", "p4", "p5"], [4, 8, 16, 32]) 13 | }, 14 | ignore_value=255, 15 | num_classes=54, # COCO stuff + 1 16 | conv_dims=128, 17 | common_stride=4, 18 | loss_weight=0.5, 19 | norm="GN", 20 | ) 21 | -------------------------------------------------------------------------------- /det/configs/common/optim.py: -------------------------------------------------------------------------------- 1 | import torch 2 | 3 | from detectron2.config import LazyCall as L 4 | from detectron2.solver.build import get_default_optimizer_params 5 | 6 | SGD = L(torch.optim.SGD)( 7 | params=L(get_default_optimizer_params)( 8 | # params.model is meant to be set to the model object, before instantiating 9 | # the optimizer. 10 | weight_decay_norm=0.0 11 | ), 12 | lr=0.02, 13 | momentum=0.9, 14 | weight_decay=1e-4, 15 | ) 16 | 17 | 18 | AdamW = L(torch.optim.AdamW)( 19 | params=L(get_default_optimizer_params)( 20 | # params.model is meant to be set to the model object, before instantiating 21 | # the optimizer. 22 | base_lr="${..lr}", 23 | weight_decay_norm=0.0, 24 | ), 25 | lr=1e-4, 26 | betas=(0.9, 0.999), 27 | weight_decay=0.1, 28 | ) 29 | -------------------------------------------------------------------------------- /det/configs/common/train.py: -------------------------------------------------------------------------------- 1 | # Common training-related configs that are designed for "tools/lazyconfig_train_net.py" 2 | # You can use your own instead, together with your own train_net.py 3 | train = dict( 4 | output_dir="./output", 5 | init_checkpoint="", 6 | max_iter=90000, 7 | amp=dict(enabled=False), # options for Automatic Mixed Precision 8 | ddp=dict( # options for DistributedDataParallel 9 | broadcast_buffers=False, 10 | find_unused_parameters=False, 11 | fp16_compression=False, 12 | ), 13 | checkpointer=dict(period=5000, max_to_keep=100), # options for PeriodicCheckpointer 14 | eval_period=5000, 15 | log_period=20, 16 | device="cuda" 17 | # ... 18 | ) 19 | -------------------------------------------------------------------------------- /det/configs/new_baselines/mask_rcnn_R_101_FPN_100ep_LSJ.py: -------------------------------------------------------------------------------- 1 | from .mask_rcnn_R_50_FPN_100ep_LSJ import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | optimizer, 6 | train, 7 | ) 8 | 9 | model.backbone.bottom_up.stages.depth = 101 10 | -------------------------------------------------------------------------------- /det/configs/new_baselines/mask_rcnn_R_101_FPN_200ep_LSJ.py: -------------------------------------------------------------------------------- 1 | from .mask_rcnn_R_101_FPN_100ep_LSJ import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | optimizer, 6 | train, 7 | ) 8 | 9 | train.max_iter *= 2 # 100ep -> 200ep 10 | 11 | lr_multiplier.scheduler.milestones = [ 12 | milestone * 2 for milestone in lr_multiplier.scheduler.milestones 13 | ] 14 | lr_multiplier.scheduler.num_updates = train.max_iter 15 | -------------------------------------------------------------------------------- /det/configs/new_baselines/mask_rcnn_R_101_FPN_400ep_LSJ.py: -------------------------------------------------------------------------------- 1 | from .mask_rcnn_R_101_FPN_100ep_LSJ import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | optimizer, 6 | train, 7 | ) 8 | 9 | train.max_iter *= 4 # 100ep -> 400ep 10 | 11 | lr_multiplier.scheduler.milestones = [ 12 | milestone * 4 for milestone in lr_multiplier.scheduler.milestones 13 | ] 14 | lr_multiplier.scheduler.num_updates = train.max_iter 15 | -------------------------------------------------------------------------------- /det/configs/new_baselines/mask_rcnn_R_50_FPN_200ep_LSJ.py: -------------------------------------------------------------------------------- 1 | from .mask_rcnn_R_50_FPN_100ep_LSJ import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | optimizer, 6 | train, 7 | ) 8 | 9 | train.max_iter *= 2 # 100ep -> 200ep 10 | 11 | lr_multiplier.scheduler.milestones = [ 12 | milestone * 2 for milestone in lr_multiplier.scheduler.milestones 13 | ] 14 | lr_multiplier.scheduler.num_updates = train.max_iter 15 | -------------------------------------------------------------------------------- /det/configs/new_baselines/mask_rcnn_R_50_FPN_400ep_LSJ.py: -------------------------------------------------------------------------------- 1 | from .mask_rcnn_R_50_FPN_100ep_LSJ import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | optimizer, 6 | train, 7 | ) 8 | 9 | train.max_iter *= 4 # 100ep -> 400ep 10 | 11 | lr_multiplier.scheduler.milestones = [ 12 | milestone * 4 for milestone in lr_multiplier.scheduler.milestones 13 | ] 14 | lr_multiplier.scheduler.num_updates = train.max_iter 15 | -------------------------------------------------------------------------------- /det/configs/new_baselines/mask_rcnn_R_50_FPN_50ep_LSJ.py: -------------------------------------------------------------------------------- 1 | from .mask_rcnn_R_50_FPN_100ep_LSJ import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | optimizer, 6 | train, 7 | ) 8 | 9 | train.max_iter //= 2 # 100ep -> 50ep 10 | 11 | lr_multiplier.scheduler.milestones = [ 12 | milestone // 2 for milestone in lr_multiplier.scheduler.milestones 13 | ] 14 | lr_multiplier.scheduler.num_updates = train.max_iter 15 | -------------------------------------------------------------------------------- /det/configs/new_baselines/mask_rcnn_regnetx_4gf_dds_FPN_100ep_LSJ.py: -------------------------------------------------------------------------------- 1 | from .mask_rcnn_R_50_FPN_100ep_LSJ import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | optimizer, 6 | train, 7 | ) 8 | from detectron2.config import LazyCall as L 9 | from detectron2.modeling.backbone import RegNet 10 | from detectron2.modeling.backbone.regnet import SimpleStem, ResBottleneckBlock 11 | 12 | # Config source: 13 | # https://github.com/facebookresearch/detectron2/blob/main/configs/COCO-InstanceSegmentation/mask_rcnn_regnetx_4gf_dds_fpn_1x.py # noqa 14 | model.backbone.bottom_up = L(RegNet)( 15 | stem_class=SimpleStem, 16 | stem_width=32, 17 | block_class=ResBottleneckBlock, 18 | depth=23, 19 | w_a=38.65, 20 | w_0=96, 21 | w_m=2.43, 22 | group_width=40, 23 | norm="SyncBN", 24 | out_features=["s1", "s2", "s3", "s4"], 25 | ) 26 | model.pixel_std = [57.375, 57.120, 58.395] 27 | 28 | # RegNets benefit from enabling cudnn benchmark mode 29 | train.cudnn_benchmark = True 30 | -------------------------------------------------------------------------------- /det/configs/new_baselines/mask_rcnn_regnetx_4gf_dds_FPN_200ep_LSJ.py: -------------------------------------------------------------------------------- 1 | from .mask_rcnn_regnetx_4gf_dds_FPN_100ep_LSJ import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | optimizer, 6 | train, 7 | ) 8 | 9 | train.max_iter *= 2 # 100ep -> 200ep 10 | 11 | lr_multiplier.scheduler.milestones = [ 12 | milestone * 2 for milestone in lr_multiplier.scheduler.milestones 13 | ] 14 | lr_multiplier.scheduler.num_updates = train.max_iter 15 | -------------------------------------------------------------------------------- /det/configs/new_baselines/mask_rcnn_regnetx_4gf_dds_FPN_400ep_LSJ.py: -------------------------------------------------------------------------------- 1 | from .mask_rcnn_regnetx_4gf_dds_FPN_100ep_LSJ import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | optimizer, 6 | train, 7 | ) 8 | 9 | train.max_iter *= 4 # 100ep -> 400ep 10 | 11 | lr_multiplier.scheduler.milestones = [ 12 | milestone * 4 for milestone in lr_multiplier.scheduler.milestones 13 | ] 14 | lr_multiplier.scheduler.num_updates = train.max_iter 15 | -------------------------------------------------------------------------------- /det/configs/new_baselines/mask_rcnn_regnety_4gf_dds_FPN_200ep_LSJ.py: -------------------------------------------------------------------------------- 1 | from .mask_rcnn_regnety_4gf_dds_FPN_100ep_LSJ import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | optimizer, 6 | train, 7 | ) 8 | 9 | train.max_iter *= 2 # 100ep -> 200ep 10 | 11 | lr_multiplier.scheduler.milestones = [ 12 | milestone * 2 for milestone in lr_multiplier.scheduler.milestones 13 | ] 14 | lr_multiplier.scheduler.num_updates = train.max_iter 15 | -------------------------------------------------------------------------------- /det/configs/new_baselines/mask_rcnn_regnety_4gf_dds_FPN_400ep_LSJ.py: -------------------------------------------------------------------------------- 1 | from .mask_rcnn_regnety_4gf_dds_FPN_100ep_LSJ import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | optimizer, 6 | train, 7 | ) 8 | 9 | train.max_iter *= 4 # 100ep -> 400ep 10 | 11 | lr_multiplier.scheduler.milestones = [ 12 | milestone * 4 for milestone in lr_multiplier.scheduler.milestones 13 | ] 14 | lr_multiplier.scheduler.num_updates = train.max_iter 15 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/README.md: -------------------------------------------------------------------------------- 1 | These are quick configs for performance or accuracy regression tracking purposes. 2 | 3 | * `*instance_test.yaml`: can train on 2 GPUs. They are used to test whether the training can 4 | successfully finish. They are not expected to produce reasonable training results. 5 | * `*inference_acc_test.yaml`: They should be run using `--eval-only`. They run inference using pre-trained models and verify 6 | the results are as expected. 7 | * `*training_acc_test.yaml`: They should be trained on 8 GPUs. They finish in about an hour and verify the training accuracy 8 | is within the normal range. 9 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/cascade_mask_rcnn_R_50_FPN_inference_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Misc/cascade_mask_rcnn_R_50_FPN_3x.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://Misc/cascade_mask_rcnn_R_50_FPN_3x/144998488/model_final_480dd8.pkl" 4 | DATASETS: 5 | TEST: ("coco_2017_val_100",) 6 | TEST: 7 | EXPECTED_RESULTS: [["bbox", "AP", 50.18, 0.02], ["segm", "AP", 43.87, 0.02]] 8 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/cascade_mask_rcnn_R_50_FPN_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Misc/cascade_mask_rcnn_R_50_FPN_3x.yaml" 2 | DATASETS: 3 | TRAIN: ("coco_2017_val_100",) 4 | TEST: ("coco_2017_val_100",) 5 | SOLVER: 6 | BASE_LR: 0.005 7 | STEPS: (30,) 8 | MAX_ITER: 40 9 | IMS_PER_BATCH: 4 10 | DATALOADER: 11 | NUM_WORKERS: 2 12 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/fast_rcnn_R_50_FPN_inference_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://COCO-Detection/fast_rcnn_R_50_FPN_1x/137635226/model_final_e5f7ce.pkl" 4 | DATASETS: 5 | TEST: ("coco_2017_val_100",) 6 | TEST: 7 | EXPECTED_RESULTS: [["bbox", "AP", 45.70, 0.02]] 8 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/fast_rcnn_R_50_FPN_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | DATASETS: 5 | TRAIN: ("coco_2017_val_100",) 6 | PROPOSAL_FILES_TRAIN: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_val_box_proposals_ee0dad.pkl", ) 7 | TEST: ("coco_2017_val_100",) 8 | PROPOSAL_FILES_TEST: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_val_box_proposals_ee0dad.pkl", ) 9 | SOLVER: 10 | BASE_LR: 0.005 11 | STEPS: (30,) 12 | MAX_ITER: 40 13 | IMS_PER_BATCH: 4 14 | DATALOADER: 15 | NUM_WORKERS: 2 16 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/keypoint_rcnn_R_50_FPN_inference_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x/137849621/model_final_a6e10b.pkl" 4 | DATASETS: 5 | TEST: ("keypoints_coco_2017_val_100",) 6 | TEST: 7 | EXPECTED_RESULTS: [["bbox", "AP", 52.47, 0.02], ["keypoints", "AP", 67.36, 0.02]] 8 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/keypoint_rcnn_R_50_FPN_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | KEYPOINT_ON: True 5 | ROI_HEADS: 6 | NUM_CLASSES: 1 7 | DATASETS: 8 | TRAIN: ("keypoints_coco_2017_val_100",) 9 | TEST: ("keypoints_coco_2017_val_100",) 10 | SOLVER: 11 | BASE_LR: 0.005 12 | STEPS: (30,) 13 | MAX_ITER: 40 14 | IMS_PER_BATCH: 4 15 | DATALOADER: 16 | NUM_WORKERS: 2 17 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/keypoint_rcnn_R_50_FPN_training_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | KEYPOINT_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | ROI_HEADS: 8 | BATCH_SIZE_PER_IMAGE: 256 9 | NUM_CLASSES: 1 10 | ROI_KEYPOINT_HEAD: 11 | POOLER_RESOLUTION: 14 12 | POOLER_SAMPLING_RATIO: 2 13 | ROI_BOX_HEAD: 14 | SMOOTH_L1_BETA: 1.0 # Keypoint AP degrades when using plain L1 loss 15 | RPN: 16 | SMOOTH_L1_BETA: 0.2 # Keypoint AP degrades when using plain L1 loss 17 | DATASETS: 18 | TRAIN: ("keypoints_coco_2017_val",) 19 | TEST: ("keypoints_coco_2017_val",) 20 | INPUT: 21 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 22 | SOLVER: 23 | WARMUP_FACTOR: 0.33333333 24 | WARMUP_ITERS: 100 25 | STEPS: (5500, 5800) 26 | MAX_ITER: 6000 27 | TEST: 28 | EXPECTED_RESULTS: [["bbox", "AP", 53.5, 1.0], ["keypoints", "AP", 72.4, 1.0]] 29 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/mask_rcnn_R_50_C4_GCV_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-C4.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | DATASETS: 6 | TRAIN: ("coco_2017_val_100",) 7 | TEST: ("coco_2017_val_100",) 8 | SOLVER: 9 | BASE_LR: 0.001 10 | STEPS: (30,) 11 | MAX_ITER: 40 12 | IMS_PER_BATCH: 4 13 | CLIP_GRADIENTS: 14 | ENABLED: True 15 | CLIP_TYPE: "value" 16 | CLIP_VALUE: 1.0 17 | DATALOADER: 18 | NUM_WORKERS: 2 19 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/mask_rcnn_R_50_C4_inference_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x/137849525/model_final_4ce675.pkl" 4 | DATASETS: 5 | TEST: ("coco_2017_val_100",) 6 | TEST: 7 | EXPECTED_RESULTS: [["bbox", "AP", 47.37, 0.02], ["segm", "AP", 40.99, 0.02]] 8 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/mask_rcnn_R_50_C4_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-C4.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | DATASETS: 6 | TRAIN: ("coco_2017_val_100",) 7 | TEST: ("coco_2017_val_100",) 8 | SOLVER: 9 | BASE_LR: 0.001 10 | STEPS: (30,) 11 | MAX_ITER: 40 12 | IMS_PER_BATCH: 4 13 | DATALOADER: 14 | NUM_WORKERS: 2 15 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/mask_rcnn_R_50_C4_training_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-C4.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | ROI_HEADS: 5 | BATCH_SIZE_PER_IMAGE: 256 6 | MASK_ON: True 7 | DATASETS: 8 | TRAIN: ("coco_2017_val",) 9 | TEST: ("coco_2017_val",) 10 | INPUT: 11 | MIN_SIZE_TRAIN: (600,) 12 | MAX_SIZE_TRAIN: 1000 13 | MIN_SIZE_TEST: 800 14 | MAX_SIZE_TEST: 1000 15 | SOLVER: 16 | IMS_PER_BATCH: 8 # base uses 16 17 | WARMUP_FACTOR: 0.33333 18 | WARMUP_ITERS: 100 19 | STEPS: (11000, 11600) 20 | MAX_ITER: 12000 21 | TEST: 22 | EXPECTED_RESULTS: [["bbox", "AP", 41.88, 0.7], ["segm", "AP", 33.79, 0.5]] 23 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/mask_rcnn_R_50_DC5_inference_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x/137849551/model_final_84107b.pkl" 4 | DATASETS: 5 | TEST: ("coco_2017_val_100",) 6 | TEST: 7 | EXPECTED_RESULTS: [["bbox", "AP", 47.44, 0.02], ["segm", "AP", 42.94, 0.02]] 8 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/mask_rcnn_R_50_FPN_inference_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl" 4 | DATASETS: 5 | TEST: ("coco_2017_val_100",) 6 | TEST: 7 | EXPECTED_RESULTS: [["bbox", "AP", 47.34, 0.02], ["segm", "AP", 42.67, 0.02], ["bbox_TTA", "AP", 49.11, 0.02], ["segm_TTA", "AP", 45.04, 0.02]] 8 | AUG: 9 | ENABLED: True 10 | MIN_SIZES: (700, 800) # to save some time 11 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/mask_rcnn_R_50_FPN_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | DATASETS: 6 | TRAIN: ("coco_2017_val_100",) 7 | TEST: ("coco_2017_val_100",) 8 | SOLVER: 9 | BASE_LR: 0.005 10 | STEPS: (30,) 11 | MAX_ITER: 40 12 | IMS_PER_BATCH: 4 13 | DATALOADER: 14 | NUM_WORKERS: 2 15 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/mask_rcnn_R_50_FPN_pred_boxes_training_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "./mask_rcnn_R_50_FPN_training_acc_test.yaml" 2 | MODEL: 3 | ROI_BOX_HEAD: 4 | TRAIN_ON_PRED_BOXES: True 5 | TEST: 6 | EXPECTED_RESULTS: [["bbox", "AP", 42.6, 1.0], ["segm", "AP", 35.8, 0.8]] 7 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/mask_rcnn_R_50_FPN_training_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | ROI_HEADS: 5 | BATCH_SIZE_PER_IMAGE: 256 6 | MASK_ON: True 7 | DATASETS: 8 | TRAIN: ("coco_2017_val",) 9 | TEST: ("coco_2017_val",) 10 | INPUT: 11 | MIN_SIZE_TRAIN: (600,) 12 | MAX_SIZE_TRAIN: 1000 13 | MIN_SIZE_TEST: 800 14 | MAX_SIZE_TEST: 1000 15 | SOLVER: 16 | WARMUP_FACTOR: 0.3333333 17 | WARMUP_ITERS: 100 18 | STEPS: (5500, 5800) 19 | MAX_ITER: 6000 20 | TEST: 21 | EXPECTED_RESULTS: [["bbox", "AP", 42.5, 1.0], ["segm", "AP", 35.8, 0.8]] 22 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/panoptic_fpn_R_50_inference_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../COCO-PanopticSegmentation/panoptic_fpn_R_50_3x.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://COCO-PanopticSegmentation/panoptic_fpn_R_50_3x/139514569/model_final_c10459.pkl" 4 | DATASETS: 5 | TEST: ("coco_2017_val_100_panoptic_separated",) 6 | TEST: 7 | EXPECTED_RESULTS: [["bbox", "AP", 46.47, 0.02], ["segm", "AP", 43.39, 0.02], ["sem_seg", "mIoU", 42.55, 0.02], ["panoptic_seg", "PQ", 38.99, 0.02]] 8 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/panoptic_fpn_R_50_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | META_ARCHITECTURE: "PanopticFPN" 4 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 5 | MASK_ON: True 6 | RESNETS: 7 | DEPTH: 50 8 | SEM_SEG_HEAD: 9 | LOSS_WEIGHT: 0.5 10 | DATASETS: 11 | TRAIN: ("coco_2017_val_100_panoptic_separated",) 12 | TEST: ("coco_2017_val_100_panoptic_separated",) 13 | SOLVER: 14 | BASE_LR: 0.005 15 | STEPS: (30,) 16 | MAX_ITER: 40 17 | IMS_PER_BATCH: 4 18 | DATALOADER: 19 | NUM_WORKERS: 1 20 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/panoptic_fpn_R_50_training_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | META_ARCHITECTURE: "PanopticFPN" 4 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 5 | MASK_ON: True 6 | RESNETS: 7 | DEPTH: 50 8 | SEM_SEG_HEAD: 9 | LOSS_WEIGHT: 0.5 10 | DATASETS: 11 | TRAIN: ("coco_2017_val_panoptic_separated",) 12 | TEST: ("coco_2017_val_panoptic_separated",) 13 | SOLVER: 14 | BASE_LR: 0.01 15 | WARMUP_FACTOR: 0.001 16 | WARMUP_ITERS: 500 17 | STEPS: (5500,) 18 | MAX_ITER: 7000 19 | TEST: 20 | EXPECTED_RESULTS: [["bbox", "AP", 46.70, 1.1], ["segm", "AP", 39.0, 0.7], ["sem_seg", "mIoU", 64.73, 1.3], ["panoptic_seg", "PQ", 48.13, 0.8]] 21 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/retinanet_R_50_FPN_inference_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../COCO-Detection/retinanet_R_50_FPN_3x.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://COCO-Detection/retinanet_R_50_FPN_3x/190397829/model_final_5bd44e.pkl" 4 | DATASETS: 5 | TEST: ("coco_2017_val_100",) 6 | TEST: 7 | EXPECTED_RESULTS: [["bbox", "AP", 44.45, 0.02]] 8 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/retinanet_R_50_FPN_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../COCO-Detection/retinanet_R_50_FPN_1x.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | DATASETS: 5 | TRAIN: ("coco_2017_val_100",) 6 | TEST: ("coco_2017_val_100",) 7 | SOLVER: 8 | BASE_LR: 0.005 9 | STEPS: (30,) 10 | MAX_ITER: 40 11 | IMS_PER_BATCH: 4 12 | DATALOADER: 13 | NUM_WORKERS: 2 14 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/rpn_R_50_FPN_inference_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../COCO-Detection/rpn_R_50_FPN_1x.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/model_final_02ce48.pkl" 4 | DATASETS: 5 | TEST: ("coco_2017_val_100",) 6 | TEST: 7 | EXPECTED_RESULTS: [["box_proposals", "AR@1000", 58.16, 0.02]] 8 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/rpn_R_50_FPN_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../COCO-Detection/rpn_R_50_FPN_1x.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | DATASETS: 5 | TRAIN: ("coco_2017_val_100",) 6 | TEST: ("coco_2017_val_100",) 7 | SOLVER: 8 | STEPS: (30,) 9 | MAX_ITER: 40 10 | BASE_LR: 0.005 11 | IMS_PER_BATCH: 4 12 | DATALOADER: 13 | NUM_WORKERS: 2 14 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/semantic_R_50_FPN_inference_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | META_ARCHITECTURE: "SemanticSegmentor" 4 | WEIGHTS: "detectron2://semantic_R_50_FPN_1x/111802073/model_final_c18079783c55a94968edc28b7101c5f0.pkl" 5 | RESNETS: 6 | DEPTH: 50 7 | DATASETS: 8 | TEST: ("coco_2017_val_100_panoptic_stuffonly",) 9 | TEST: 10 | EXPECTED_RESULTS: [["sem_seg", "mIoU", 39.53, 0.02], ["sem_seg", "mACC", 51.50, 0.02]] 11 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/semantic_R_50_FPN_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | META_ARCHITECTURE: "SemanticSegmentor" 4 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 5 | RESNETS: 6 | DEPTH: 50 7 | DATASETS: 8 | TRAIN: ("coco_2017_val_100_panoptic_stuffonly",) 9 | TEST: ("coco_2017_val_100_panoptic_stuffonly",) 10 | INPUT: 11 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 12 | SOLVER: 13 | BASE_LR: 0.005 14 | STEPS: (30,) 15 | MAX_ITER: 40 16 | IMS_PER_BATCH: 4 17 | DATALOADER: 18 | NUM_WORKERS: 2 19 | -------------------------------------------------------------------------------- /det/configs/quick_schedules/semantic_R_50_FPN_training_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-RCNN-FPN.yaml" 2 | MODEL: 3 | META_ARCHITECTURE: "SemanticSegmentor" 4 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 5 | RESNETS: 6 | DEPTH: 50 7 | DATASETS: 8 | TRAIN: ("coco_2017_val_panoptic_stuffonly",) 9 | TEST: ("coco_2017_val_panoptic_stuffonly",) 10 | SOLVER: 11 | BASE_LR: 0.01 12 | WARMUP_FACTOR: 0.001 13 | WARMUP_ITERS: 300 14 | STEPS: (5500,) 15 | MAX_ITER: 7000 16 | TEST: 17 | EXPECTED_RESULTS: [["sem_seg", "mIoU", 76.51, 1.0], ["sem_seg", "mACC", 83.25, 1.0]] 18 | INPUT: 19 | # no scale augmentation 20 | MIN_SIZE_TRAIN: (800, ) 21 | -------------------------------------------------------------------------------- /det/datasets/prepare_for_tests.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash -e 2 | # Copyright (c) Facebook, Inc. and its affiliates. 3 | 4 | # Download the mini dataset (coco val2017_100, with only 100 images) 5 | # to be used in unittests & integration tests. 6 | 7 | cd "${0%/*}" 8 | 9 | BASE=https://dl.fbaipublicfiles.com/detectron2 10 | ROOT=${DETECTRON2_DATASETS:-./} 11 | ROOT=${ROOT/#\~/$HOME} # expand ~ to HOME 12 | mkdir -p $ROOT/coco/annotations 13 | 14 | for anno in instances_val2017_100 \ 15 | person_keypoints_val2017_100 ; do 16 | 17 | dest=$ROOT/coco/annotations/$anno.json 18 | [[ -s $dest ]] && { 19 | echo "$dest exists. Skipping ..." 20 | } || { 21 | wget $BASE/annotations/coco/$anno.json -O $dest 22 | } 23 | done 24 | 25 | dest=$ROOT/coco/val2017_100.tgz 26 | [[ -d $ROOT/coco/val2017 ]] && { 27 | echo "$ROOT/coco/val2017 exists. Skipping ..." 28 | } || { 29 | wget $BASE/annotations/coco/val2017_100.tgz -O $dest 30 | tar xzf $dest -C $ROOT/coco/ && rm -f $dest 31 | } 32 | -------------------------------------------------------------------------------- /det/demo/README.md: -------------------------------------------------------------------------------- 1 | 2 | ## Detectron2 Demo 3 | 4 | We provide a command line tool to run a simple demo of builtin configs. 5 | The usage is explained in [GETTING_STARTED.md](../GETTING_STARTED.md). 6 | 7 | See our [blog post](https://ai.facebook.com/blog/-detectron2-a-pytorch-based-modular-object-detection-library-) 8 | for a high-quality demo generated with this tool. 9 | -------------------------------------------------------------------------------- /det/detectron2/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .utils.env import setup_environment 4 | 5 | setup_environment() 6 | 7 | 8 | # This line will be programatically read/write by setup.py. 9 | # Leave them at the bottom of this file and don't touch them. 10 | __version__ = "0.6" 11 | -------------------------------------------------------------------------------- /det/detectron2/checkpoint/__init__.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # Copyright (c) Facebook, Inc. and its affiliates. 3 | # File: 4 | 5 | 6 | from . import catalog as _UNUSED # register the handler 7 | from .detection_checkpoint import DetectionCheckpointer 8 | from fvcore.common.checkpoint import Checkpointer, PeriodicCheckpointer 9 | 10 | __all__ = ["Checkpointer", "PeriodicCheckpointer", "DetectionCheckpointer"] 11 | -------------------------------------------------------------------------------- /det/detectron2/config/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .compat import downgrade_config, upgrade_config 3 | from .config import CfgNode, get_cfg, global_cfg, set_global_cfg, configurable 4 | from .instantiate import instantiate 5 | from .lazy import LazyCall, LazyConfig 6 | 7 | __all__ = [ 8 | "CfgNode", 9 | "get_cfg", 10 | "global_cfg", 11 | "set_global_cfg", 12 | "downgrade_config", 13 | "upgrade_config", 14 | "configurable", 15 | "instantiate", 16 | "LazyCall", 17 | "LazyConfig", 18 | ] 19 | 20 | 21 | from detectron2.utils.env import fixup_module_metadata 22 | 23 | fixup_module_metadata(__name__, globals(), __all__) 24 | del fixup_module_metadata 25 | -------------------------------------------------------------------------------- /det/detectron2/data/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from . import transforms # isort:skip 3 | 4 | from .build import ( 5 | build_batch_data_loader, 6 | build_detection_test_loader, 7 | build_detection_train_loader, 8 | get_detection_dataset_dicts, 9 | load_proposals_into_dataset, 10 | print_instances_class_histogram, 11 | ) 12 | from .catalog import DatasetCatalog, MetadataCatalog, Metadata 13 | from .common import DatasetFromList, MapDataset, ToIterableDataset 14 | from .dataset_mapper import DatasetMapper 15 | 16 | # ensure the builtin datasets are registered 17 | from . import datasets, samplers # isort:skip 18 | 19 | __all__ = [k for k in globals().keys() if not k.startswith("_")] 20 | -------------------------------------------------------------------------------- /det/detectron2/data/datasets/README.md: -------------------------------------------------------------------------------- 1 | 2 | 3 | ### Common Datasets 4 | 5 | The dataset implemented here do not need to load the data into the final format. 6 | It should provide the minimal data structure needed to use the dataset, so it can be very efficient. 7 | 8 | For example, for an image dataset, just provide the file names and labels, but don't read the images. 9 | Let the downstream decide how to read. 10 | -------------------------------------------------------------------------------- /det/detectron2/data/datasets/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .coco import load_coco_json, load_sem_seg, register_coco_instances, convert_to_coco_json 3 | from .coco_panoptic import register_coco_panoptic, register_coco_panoptic_separated 4 | from .lvis import load_lvis_json, register_lvis_instances, get_lvis_instances_meta 5 | from .pascal_voc import load_voc_instances, register_pascal_voc 6 | from . import builtin as _builtin # ensure the builtin datasets are registered 7 | 8 | 9 | __all__ = [k for k in globals().keys() if not k.startswith("_")] 10 | -------------------------------------------------------------------------------- /det/detectron2/data/datasets/register_coco.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .coco import register_coco_instances # noqa 3 | from .coco_panoptic import register_coco_panoptic_separated # noqa 4 | -------------------------------------------------------------------------------- /det/detectron2/data/samplers/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .distributed_sampler import ( 3 | InferenceSampler, 4 | RandomSubsetTrainingSampler, 5 | RepeatFactorTrainingSampler, 6 | TrainingSampler, 7 | ) 8 | 9 | from .grouped_batch_sampler import GroupedBatchSampler 10 | 11 | __all__ = [ 12 | "GroupedBatchSampler", 13 | "TrainingSampler", 14 | "RandomSubsetTrainingSampler", 15 | "InferenceSampler", 16 | "RepeatFactorTrainingSampler", 17 | ] 18 | -------------------------------------------------------------------------------- /det/detectron2/data/transforms/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from fvcore.transforms.transform import Transform, TransformList # order them first 3 | from fvcore.transforms.transform import * 4 | from .transform import * 5 | from .augmentation import * 6 | from .augmentation_impl import * 7 | 8 | __all__ = [k for k in globals().keys() if not k.startswith("_")] 9 | 10 | 11 | from detectron2.utils.env import fixup_module_metadata 12 | 13 | fixup_module_metadata(__name__, globals(), __all__) 14 | del fixup_module_metadata 15 | -------------------------------------------------------------------------------- /det/detectron2/engine/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .launch import * 4 | from .train_loop import * 5 | 6 | __all__ = [k for k in globals().keys() if not k.startswith("_")] 7 | 8 | 9 | # prefer to let hooks and defaults live in separate namespaces (therefore not in __all__) 10 | # but still make them available here 11 | from .hooks import * 12 | from .defaults import ( 13 | create_ddp_model, 14 | default_argument_parser, 15 | default_setup, 16 | default_writers, 17 | DefaultPredictor, 18 | DefaultTrainer, 19 | ) 20 | -------------------------------------------------------------------------------- /det/detectron2/evaluation/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .cityscapes_evaluation import CityscapesInstanceEvaluator, CityscapesSemSegEvaluator 3 | from .coco_evaluation import COCOEvaluator 4 | from .rotated_coco_evaluation import RotatedCOCOEvaluator 5 | from .evaluator import DatasetEvaluator, DatasetEvaluators, inference_context, inference_on_dataset 6 | from .lvis_evaluation import LVISEvaluator 7 | from .panoptic_evaluation import COCOPanopticEvaluator 8 | from .pascal_voc_evaluation import PascalVOCDetectionEvaluator 9 | from .sem_seg_evaluation import SemSegEvaluator 10 | from .testing import print_csv_format, verify_results 11 | 12 | __all__ = [k for k in globals().keys() if not k.startswith("_")] 13 | -------------------------------------------------------------------------------- /det/detectron2/export/README.md: -------------------------------------------------------------------------------- 1 | 2 | This directory contains code to prepare a detectron2 model for deployment. 3 | Currently it supports exporting a detectron2 model to TorchScript, ONNX, or (deprecated) Caffe2 format. 4 | 5 | Please see [documentation](https://detectron2.readthedocs.io/tutorials/deployment.html) for its usage. 6 | 7 | 8 | ### Acknowledgements 9 | 10 | Thanks to Mobile Vision team at Facebook for developing the Caffe2 conversion tools. 11 | 12 | Thanks to Computing Platform Department - PAI team at Alibaba Group (@bddpqq, @chenbohua3) who 13 | help export Detectron2 models to TorchScript. 14 | 15 | Thanks to ONNX Converter team at Microsoft who help export Detectron2 models to ONNX. 16 | -------------------------------------------------------------------------------- /det/detectron2/export/__init__.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | import warnings 4 | 5 | from .flatten import TracingAdapter 6 | from .torchscript import dump_torchscript_IR, scripting_with_instances 7 | 8 | try: 9 | from caffe2.proto import caffe2_pb2 as _tmp 10 | from caffe2.python import core 11 | 12 | # caffe2 is optional 13 | except ImportError: 14 | pass 15 | else: 16 | from .api import * 17 | 18 | 19 | # TODO: Update ONNX Opset version and run tests when a newer PyTorch is supported 20 | STABLE_ONNX_OPSET_VERSION = 11 21 | 22 | 23 | def add_export_config(cfg): 24 | warnings.warn( 25 | "add_export_config has been deprecated and behaves as no-op function.", DeprecationWarning 26 | ) 27 | return cfg 28 | 29 | 30 | __all__ = [k for k in globals().keys() if not k.startswith("_")] 31 | -------------------------------------------------------------------------------- /det/detectron2/layers/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .batch_norm import FrozenBatchNorm2d, get_norm, NaiveSyncBatchNorm, CycleBatchNormList 3 | from .deform_conv import DeformConv, ModulatedDeformConv 4 | from .mask_ops import paste_masks_in_image 5 | from .nms import batched_nms, batched_nms_rotated, nms, nms_rotated 6 | from .roi_align import ROIAlign, roi_align 7 | from .roi_align_rotated import ROIAlignRotated, roi_align_rotated 8 | from .shape_spec import ShapeSpec 9 | from .wrappers import ( 10 | BatchNorm2d, 11 | Conv2d, 12 | ConvTranspose2d, 13 | cat, 14 | interpolate, 15 | Linear, 16 | nonzero_tuple, 17 | cross_entropy, 18 | empty_input_loss_func_wrapper, 19 | shapes_to_tensor, 20 | move_device_like, 21 | ) 22 | from .blocks import CNNBlockBase, DepthwiseSeparableConv2d 23 | from .aspp import ASPP 24 | from .losses import ciou_loss, diou_loss 25 | 26 | __all__ = [k for k in globals().keys() if not k.startswith("_")] 27 | -------------------------------------------------------------------------------- /det/detectron2/layers/csrc/README.md: -------------------------------------------------------------------------------- 1 | 2 | 3 | To add a new Op: 4 | 5 | 1. Create a new directory 6 | 2. Implement new ops there 7 | 3. Delcare its Python interface in `vision.cpp`. 8 | -------------------------------------------------------------------------------- /det/detectron2/layers/csrc/cuda_version.cu: -------------------------------------------------------------------------------- 1 | // Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | #include 4 | 5 | namespace detectron2 { 6 | int get_cudart_version() { 7 | // Not a ROCM platform: Either HIP is not used, or 8 | // it is used, but platform is not ROCM (i.e. it is CUDA) 9 | #if !defined(__HIP_PLATFORM_HCC__) 10 | return CUDART_VERSION; 11 | #else 12 | int version = 0; 13 | 14 | #if HIP_VERSION_MAJOR != 0 15 | // Create a convention similar to that of CUDA, as assumed by other 16 | // parts of the code. 17 | 18 | version = HIP_VERSION_MINOR; 19 | version += (HIP_VERSION_MAJOR * 100); 20 | #else 21 | hipRuntimeGetVersion(&version); 22 | #endif 23 | return version; 24 | #endif 25 | } 26 | } // namespace detectron2 27 | -------------------------------------------------------------------------------- /det/detectron2/layers/rotated_boxes.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from __future__ import absolute_import, division, print_function, unicode_literals 3 | import torch 4 | 5 | 6 | def pairwise_iou_rotated(boxes1, boxes2): 7 | """ 8 | Return intersection-over-union (Jaccard index) of boxes. 9 | 10 | Both sets of boxes are expected to be in 11 | (x_center, y_center, width, height, angle) format. 12 | 13 | Arguments: 14 | boxes1 (Tensor[N, 5]) 15 | boxes2 (Tensor[M, 5]) 16 | 17 | Returns: 18 | iou (Tensor[N, M]): the NxM matrix containing the pairwise 19 | IoU values for every element in boxes1 and boxes2 20 | """ 21 | return torch.ops.detectron2.box_iou_rotated(boxes1, boxes2) 22 | -------------------------------------------------------------------------------- /det/detectron2/layers/shape_spec.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # Copyright (c) Facebook, Inc. and its affiliates. 3 | from dataclasses import dataclass 4 | from typing import Optional 5 | 6 | 7 | @dataclass 8 | class ShapeSpec: 9 | """ 10 | A simple structure that contains basic shape specification about a tensor. 11 | It is often used as the auxiliary inputs/outputs of models, 12 | to complement the lack of shape inference ability among pytorch modules. 13 | """ 14 | 15 | channels: Optional[int] = None 16 | height: Optional[int] = None 17 | width: Optional[int] = None 18 | stride: Optional[int] = None 19 | -------------------------------------------------------------------------------- /det/detectron2/model_zoo/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | """ 3 | Model Zoo API for Detectron2: a collection of functions to create common model architectures 4 | listed in `MODEL_ZOO.md `_, 5 | and optionally load their pre-trained weights. 6 | """ 7 | 8 | from .model_zoo import get, get_config_file, get_checkpoint_url, get_config 9 | 10 | __all__ = ["get_checkpoint_url", "get", "get_config_file", "get_config"] 11 | -------------------------------------------------------------------------------- /det/detectron2/modeling/backbone/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .build import build_backbone, BACKBONE_REGISTRY # noqa F401 isort:skip 3 | 4 | from .backbone import Backbone 5 | from .fpn import FPN 6 | from .regnet import RegNet 7 | from .resnet import ( 8 | BasicStem, 9 | ResNet, 10 | ResNetBlockBase, 11 | build_resnet_backbone, 12 | make_stage, 13 | BottleneckBlock, 14 | ) 15 | from .vit import ViT, SimpleFeaturePyramid, get_vit_lr_decay_rate 16 | from .vim import VisionMambaDet, get_vim_lr_decay_rate 17 | from .mvit import MViT 18 | from .swin import SwinTransformer 19 | 20 | __all__ = [k for k in globals().keys() if not k.startswith("_")] 21 | # TODO can expose more resnet blocks after careful consideration 22 | -------------------------------------------------------------------------------- /det/detectron2/modeling/meta_arch/__init__.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # Copyright (c) Facebook, Inc. and its affiliates. 3 | 4 | from .build import META_ARCH_REGISTRY, build_model # isort:skip 5 | 6 | from .panoptic_fpn import PanopticFPN 7 | 8 | # import all the meta_arch, so they will be registered 9 | from .rcnn import GeneralizedRCNN, ProposalNetwork 10 | from .dense_detector import DenseDetector 11 | from .retinanet import RetinaNet 12 | from .fcos import FCOS 13 | from .semantic_seg import SEM_SEG_HEADS_REGISTRY, SemanticSegmentor, build_sem_seg_head 14 | 15 | 16 | __all__ = list(globals().keys()) 17 | -------------------------------------------------------------------------------- /det/detectron2/modeling/meta_arch/build.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | import torch 3 | 4 | from detectron2.utils.logger import _log_api_usage 5 | from detectron2.utils.registry import Registry 6 | 7 | META_ARCH_REGISTRY = Registry("META_ARCH") # noqa F401 isort:skip 8 | META_ARCH_REGISTRY.__doc__ = """ 9 | Registry for meta-architectures, i.e. the whole model. 10 | 11 | The registered object will be called with `obj(cfg)` 12 | and expected to return a `nn.Module` object. 13 | """ 14 | 15 | 16 | def build_model(cfg): 17 | """ 18 | Build the whole model architecture, defined by ``cfg.MODEL.META_ARCHITECTURE``. 19 | Note that it does not load any weights from ``cfg``. 20 | """ 21 | meta_arch = cfg.MODEL.META_ARCHITECTURE 22 | model = META_ARCH_REGISTRY.get(meta_arch)(cfg) 23 | model.to(torch.device(cfg.MODEL.DEVICE)) 24 | _log_api_usage("modeling.meta_arch." + meta_arch) 25 | return model 26 | -------------------------------------------------------------------------------- /det/detectron2/modeling/proposal_generator/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .build import PROPOSAL_GENERATOR_REGISTRY, build_proposal_generator 3 | from .rpn import RPN_HEAD_REGISTRY, build_rpn_head, RPN, StandardRPNHead 4 | 5 | __all__ = list(globals().keys()) 6 | -------------------------------------------------------------------------------- /det/detectron2/modeling/proposal_generator/build.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from detectron2.utils.registry import Registry 3 | 4 | PROPOSAL_GENERATOR_REGISTRY = Registry("PROPOSAL_GENERATOR") 5 | PROPOSAL_GENERATOR_REGISTRY.__doc__ = """ 6 | Registry for proposal generator, which produces object proposals from feature maps. 7 | 8 | The registered object will be called with `obj(cfg, input_shape)`. 9 | The call should return a `nn.Module` object. 10 | """ 11 | 12 | from . import rpn, rrpn # noqa F401 isort:skip 13 | 14 | 15 | def build_proposal_generator(cfg, input_shape): 16 | """ 17 | Build a proposal generator from `cfg.MODEL.PROPOSAL_GENERATOR.NAME`. 18 | The name can be "PrecomputedProposals" to use no proposal generator. 19 | """ 20 | name = cfg.MODEL.PROPOSAL_GENERATOR.NAME 21 | if name == "PrecomputedProposals": 22 | return None 23 | 24 | return PROPOSAL_GENERATOR_REGISTRY.get(name)(cfg, input_shape) 25 | -------------------------------------------------------------------------------- /det/detectron2/modeling/roi_heads/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .box_head import ROI_BOX_HEAD_REGISTRY, build_box_head, FastRCNNConvFCHead 3 | from .keypoint_head import ( 4 | ROI_KEYPOINT_HEAD_REGISTRY, 5 | build_keypoint_head, 6 | BaseKeypointRCNNHead, 7 | KRCNNConvDeconvUpsampleHead, 8 | ) 9 | from .mask_head import ( 10 | ROI_MASK_HEAD_REGISTRY, 11 | build_mask_head, 12 | BaseMaskRCNNHead, 13 | MaskRCNNConvUpsampleHead, 14 | ) 15 | from .roi_heads import ( 16 | ROI_HEADS_REGISTRY, 17 | ROIHeads, 18 | Res5ROIHeads, 19 | StandardROIHeads, 20 | build_roi_heads, 21 | select_foreground_proposals, 22 | ) 23 | from .cascade_rcnn import CascadeROIHeads 24 | from .rotated_fast_rcnn import RROIHeads 25 | from .fast_rcnn import FastRCNNOutputLayers 26 | 27 | from . import cascade_rcnn # isort:skip 28 | 29 | __all__ = list(globals().keys()) 30 | -------------------------------------------------------------------------------- /det/detectron2/projects/README.md: -------------------------------------------------------------------------------- 1 | 2 | Projects live in the [`projects` directory](../../projects) under the root of this repository, but not here. 3 | -------------------------------------------------------------------------------- /det/detectron2/solver/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .build import build_lr_scheduler, build_optimizer, get_default_optimizer_params 3 | from .lr_scheduler import ( 4 | LRMultiplier, 5 | LRScheduler, 6 | WarmupCosineLR, 7 | WarmupMultiStepLR, 8 | WarmupParamScheduler, 9 | ) 10 | 11 | __all__ = [k for k in globals().keys() if not k.startswith("_")] 12 | -------------------------------------------------------------------------------- /det/detectron2/structures/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .boxes import Boxes, BoxMode, pairwise_iou, pairwise_ioa, pairwise_point_box_distance 3 | from .image_list import ImageList 4 | 5 | from .instances import Instances 6 | from .keypoints import Keypoints, heatmaps_to_keypoints 7 | from .masks import BitMasks, PolygonMasks, polygons_to_bitmask, ROIMasks 8 | from .rotated_boxes import RotatedBoxes 9 | from .rotated_boxes import pairwise_iou as pairwise_iou_rotated 10 | 11 | __all__ = [k for k in globals().keys() if not k.startswith("_")] 12 | 13 | 14 | from detectron2.utils.env import fixup_module_metadata 15 | 16 | fixup_module_metadata(__name__, globals(), __all__) 17 | del fixup_module_metadata 18 | -------------------------------------------------------------------------------- /det/detectron2/tracking/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .base_tracker import ( # noqa 3 | BaseTracker, 4 | build_tracker_head, 5 | TRACKER_HEADS_REGISTRY, 6 | ) 7 | from .bbox_iou_tracker import BBoxIOUTracker # noqa 8 | from .hungarian_tracker import BaseHungarianTracker # noqa 9 | from .iou_weighted_hungarian_bbox_iou_tracker import ( # noqa 10 | IOUWeightedHungarianBBoxIOUTracker, 11 | ) 12 | from .utils import create_prediction_pairs # noqa 13 | from .vanilla_hungarian_bbox_iou_tracker import VanillaHungarianBBoxIOUTracker # noqa 14 | 15 | __all__ = [k for k in globals().keys() if not k.startswith("_")] 16 | -------------------------------------------------------------------------------- /det/detectron2/utils/README.md: -------------------------------------------------------------------------------- 1 | # Utility functions 2 | 3 | This folder contain utility functions that are not used in the 4 | core library, but are useful for building models or training 5 | code using the config system. 6 | -------------------------------------------------------------------------------- /det/detectron2/utils/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | -------------------------------------------------------------------------------- /det/dev/README.md: -------------------------------------------------------------------------------- 1 | 2 | ## Some scripts for developers to use, include: 3 | 4 | - `linter.sh`: lint the codebase before commit. 5 | - `run_{inference,instant}_tests.sh`: run inference/training for a few iterations. 6 | Note that these tests require 2 GPUs. 7 | - `parse_results.sh`: parse results from a log file. 8 | -------------------------------------------------------------------------------- /det/dev/packaging/README.md: -------------------------------------------------------------------------------- 1 | 2 | ## To build a cu101 wheel for release: 3 | 4 | ``` 5 | $ nvidia-docker run -it --storage-opt "size=20GB" --name pt pytorch/manylinux-cuda101 6 | # inside the container: 7 | # git clone https://github.com/facebookresearch/detectron2/ 8 | # cd detectron2 9 | # export CU_VERSION=cu101 D2_VERSION_SUFFIX= PYTHON_VERSION=3.7 PYTORCH_VERSION=1.8 10 | # ./dev/packaging/build_wheel.sh 11 | ``` 12 | 13 | ## To build all wheels for combinations of CUDA and Python 14 | ``` 15 | ./dev/packaging/build_all_wheels.sh 16 | ./dev/packaging/gen_wheel_index.sh /path/to/wheels 17 | ``` 18 | -------------------------------------------------------------------------------- /det/dev/run_instant_tests.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash -e 2 | # Copyright (c) Facebook, Inc. and its affiliates. 3 | 4 | BIN="python tools/train_net.py" 5 | OUTPUT="instant_test_output" 6 | NUM_GPUS=2 7 | 8 | CFG_LIST=( "${@:1}" ) 9 | if [ ${#CFG_LIST[@]} -eq 0 ]; then 10 | CFG_LIST=( ./configs/quick_schedules/*instant_test.yaml ) 11 | fi 12 | 13 | echo "========================================================================" 14 | echo "Configs to run:" 15 | echo "${CFG_LIST[@]}" 16 | echo "========================================================================" 17 | 18 | for cfg in "${CFG_LIST[@]}"; do 19 | echo "========================================================================" 20 | echo "Running $cfg ..." 21 | echo "========================================================================" 22 | $BIN --num-gpus $NUM_GPUS --config-file "$cfg" \ 23 | SOLVER.IMS_PER_BATCH $(($NUM_GPUS * 2)) \ 24 | OUTPUT_DIR "$OUTPUT" 25 | rm -rf "$OUTPUT" 26 | done 27 | 28 | -------------------------------------------------------------------------------- /det/docker/docker-compose.yml: -------------------------------------------------------------------------------- 1 | version: "2.3" 2 | services: 3 | detectron2: 4 | build: 5 | context: . 6 | dockerfile: Dockerfile 7 | args: 8 | USER_ID: ${USER_ID:-1000} 9 | deploy: 10 | resources: 11 | reservations: 12 | devices: 13 | - capabilities: 14 | - gpu 15 | shm_size: "8gb" 16 | ulimits: 17 | memlock: -1 18 | stack: 67108864 19 | volumes: 20 | - /tmp/.X11-unix:/tmp/.X11-unix:ro 21 | environment: 22 | - DISPLAY=$DISPLAY 23 | - NVIDIA_VISIBLE_DEVICES=all 24 | # Uncomment with proper source to access webcam from docker 25 | # devices: 26 | # - /dev/video0:/dev/video0 27 | -------------------------------------------------------------------------------- /det/docs/.gitignore: -------------------------------------------------------------------------------- 1 | _build 2 | -------------------------------------------------------------------------------- /det/docs/Makefile: -------------------------------------------------------------------------------- 1 | # Minimal makefile for Sphinx documentation 2 | # Copyright (c) Facebook, Inc. and its affiliates. 3 | 4 | # You can set these variables from the command line. 5 | SPHINXOPTS = 6 | SPHINXBUILD = sphinx-build 7 | SOURCEDIR = . 8 | BUILDDIR = _build 9 | 10 | # Put it first so that "make" without argument is like "make help". 11 | help: 12 | @$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) 13 | 14 | .PHONY: help Makefile 15 | 16 | # Catch-all target: route all unknown targets to Sphinx using the new 17 | # "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS). 18 | %: Makefile 19 | @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) 20 | -------------------------------------------------------------------------------- /det/docs/README.md: -------------------------------------------------------------------------------- 1 | # Read the docs: 2 | 3 | The latest documentation built from this directory is available at [detectron2.readthedocs.io](https://detectron2.readthedocs.io/). 4 | Documents in this directory are not meant to be read on github. 5 | 6 | # Build the docs: 7 | 8 | 1. Install detectron2 according to [INSTALL.md](../INSTALL.md). 9 | 2. Install additional libraries required to build docs: 10 | - docutils==0.16 11 | - Sphinx==3.2.0 12 | - recommonmark==0.6.0 13 | - sphinx_rtd_theme 14 | 15 | 3. Run `make html` from this directory. 16 | -------------------------------------------------------------------------------- /det/docs/_static/css/custom.css: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright (c) Facebook, Inc. and its affiliates. 3 | * some extra css to make markdown look similar between github/sphinx 4 | */ 5 | 6 | /* 7 | * Below is for install.md: 8 | */ 9 | .rst-content code { 10 | white-space: pre; 11 | border: 0px; 12 | } 13 | 14 | .rst-content th { 15 | border: 1px solid #e1e4e5; 16 | } 17 | 18 | .rst-content th p { 19 | /* otherwise will be default 24px for regular paragraph */ 20 | margin-bottom: 0px; 21 | } 22 | 23 | .rst-content .line-block { 24 | /* otherwise will be 24px */ 25 | margin-bottom: 0px; 26 | } 27 | 28 | div.section > details { 29 | padding-bottom: 1em; 30 | } 31 | -------------------------------------------------------------------------------- /det/docs/index.rst: -------------------------------------------------------------------------------- 1 | .. detectron2 documentation master file, created by 2 | sphinx-quickstart on Sat Sep 21 13:46:45 2019. 3 | You can adapt this file completely to your liking, but it should at least 4 | contain the root `toctree` directive. 5 | 6 | Welcome to detectron2's documentation! 7 | ====================================== 8 | 9 | .. toctree:: 10 | :maxdepth: 2 11 | 12 | tutorials/index 13 | notes/index 14 | modules/index 15 | -------------------------------------------------------------------------------- /det/docs/modules/checkpoint.rst: -------------------------------------------------------------------------------- 1 | detectron2.checkpoint 2 | ============================= 3 | 4 | .. automodule:: detectron2.checkpoint 5 | :members: 6 | :undoc-members: 7 | :show-inheritance: 8 | -------------------------------------------------------------------------------- /det/docs/modules/config.rst: -------------------------------------------------------------------------------- 1 | detectron2.config 2 | ========================= 3 | 4 | Related tutorials: :doc:`../tutorials/configs`, :doc:`../tutorials/extend`. 5 | 6 | .. automodule:: detectron2.config 7 | :members: 8 | :undoc-members: 9 | :show-inheritance: 10 | 11 | 12 | Yaml Config References 13 | ----------------- 14 | 15 | .. literalinclude:: ../../detectron2/config/defaults.py 16 | :language: python 17 | :linenos: 18 | :lines: 7- 19 | -------------------------------------------------------------------------------- /det/docs/modules/data.rst: -------------------------------------------------------------------------------- 1 | detectron2.data 2 | ======================= 3 | 4 | .. autodata:: detectron2.data.DatasetCatalog(dict) 5 | :annotation: 6 | 7 | .. autodata:: detectron2.data.MetadataCatalog(dict) 8 | :annotation: 9 | 10 | .. automodule:: detectron2.data 11 | :members: 12 | :undoc-members: 13 | :show-inheritance: 14 | 15 | detectron2.data.detection\_utils module 16 | --------------------------------------- 17 | 18 | .. automodule:: detectron2.data.detection_utils 19 | :members: 20 | :undoc-members: 21 | :show-inheritance: 22 | 23 | detectron2.data.datasets module 24 | --------------------------------------- 25 | 26 | .. automodule:: detectron2.data.datasets 27 | :members: 28 | :undoc-members: 29 | :show-inheritance: 30 | 31 | detectron2.data.samplers module 32 | --------------------------------------- 33 | 34 | .. automodule:: detectron2.data.samplers 35 | :members: 36 | :undoc-members: 37 | :show-inheritance: 38 | -------------------------------------------------------------------------------- /det/docs/modules/data_transforms.rst: -------------------------------------------------------------------------------- 1 | detectron2.data.transforms 2 | ==================================== 3 | 4 | Related tutorial: :doc:`../tutorials/augmentation`. 5 | 6 | .. automodule:: detectron2.data.transforms 7 | :members: 8 | :undoc-members: 9 | :show-inheritance: 10 | :imported-members: 11 | -------------------------------------------------------------------------------- /det/docs/modules/engine.rst: -------------------------------------------------------------------------------- 1 | detectron2.engine 2 | ========================= 3 | 4 | Related tutorial: :doc:`../tutorials/training`. 5 | 6 | .. automodule:: detectron2.engine 7 | :members: 8 | :undoc-members: 9 | :show-inheritance: 10 | 11 | 12 | detectron2.engine.defaults module 13 | --------------------------------- 14 | 15 | .. automodule:: detectron2.engine.defaults 16 | :members: 17 | :undoc-members: 18 | :show-inheritance: 19 | 20 | detectron2.engine.hooks module 21 | --------------------------------- 22 | 23 | .. automodule:: detectron2.engine.hooks 24 | :members: 25 | :undoc-members: 26 | :show-inheritance: 27 | -------------------------------------------------------------------------------- /det/docs/modules/evaluation.rst: -------------------------------------------------------------------------------- 1 | detectron2.evaluation 2 | ============================= 3 | 4 | .. automodule:: detectron2.evaluation 5 | :members: 6 | :undoc-members: 7 | :show-inheritance: 8 | -------------------------------------------------------------------------------- /det/docs/modules/export.rst: -------------------------------------------------------------------------------- 1 | detectron2.export 2 | ========================= 3 | 4 | Related tutorial: :doc:`../tutorials/deployment`. 5 | 6 | .. automodule:: detectron2.export 7 | :members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /det/docs/modules/index.rst: -------------------------------------------------------------------------------- 1 | API Documentation 2 | ================== 3 | 4 | .. toctree:: 5 | 6 | checkpoint 7 | config 8 | data 9 | data_transforms 10 | engine 11 | evaluation 12 | layers 13 | model_zoo 14 | modeling 15 | solver 16 | structures 17 | utils 18 | export 19 | fvcore 20 | -------------------------------------------------------------------------------- /det/docs/modules/layers.rst: -------------------------------------------------------------------------------- 1 | detectron2.layers 2 | ========================= 3 | 4 | .. automodule:: detectron2.layers 5 | :members: 6 | :undoc-members: 7 | :show-inheritance: 8 | -------------------------------------------------------------------------------- /det/docs/modules/model_zoo.rst: -------------------------------------------------------------------------------- 1 | detectron2.model_zoo 2 | ============================ 3 | 4 | .. automodule:: detectron2.model_zoo 5 | :members: 6 | :undoc-members: 7 | :show-inheritance: 8 | -------------------------------------------------------------------------------- /det/docs/modules/solver.rst: -------------------------------------------------------------------------------- 1 | detectron2.solver 2 | ========================= 3 | 4 | .. automodule:: detectron2.solver 5 | :members: 6 | :undoc-members: 7 | :show-inheritance: 8 | -------------------------------------------------------------------------------- /det/docs/modules/structures.rst: -------------------------------------------------------------------------------- 1 | detectron2.structures 2 | ============================= 3 | 4 | .. automodule:: detectron2.structures 5 | :members: 6 | :undoc-members: 7 | :show-inheritance: 8 | -------------------------------------------------------------------------------- /det/docs/notes/contributing.md: -------------------------------------------------------------------------------- 1 | ../../.github/CONTRIBUTING.md -------------------------------------------------------------------------------- /det/docs/notes/index.rst: -------------------------------------------------------------------------------- 1 | Notes 2 | ====================================== 3 | 4 | .. toctree:: 5 | :maxdepth: 2 6 | 7 | benchmarks 8 | compatibility 9 | contributing 10 | changelog 11 | -------------------------------------------------------------------------------- /det/docs/requirements.txt: -------------------------------------------------------------------------------- 1 | docutils==0.16 2 | # https://github.com/sphinx-doc/sphinx/commit/7acd3ada3f38076af7b2b5c9f3b60bb9c2587a3d 3 | sphinx==3.2.0 4 | recommonmark==0.6.0 5 | sphinx_rtd_theme 6 | # Dependencies here are only those required by import 7 | termcolor 8 | numpy 9 | tqdm 10 | matplotlib 11 | termcolor 12 | yacs 13 | tabulate 14 | cloudpickle 15 | Pillow 16 | future 17 | git+https://github.com/facebookresearch/fvcore.git 18 | https://download.pytorch.org/whl/cpu/torch-1.8.1%2Bcpu-cp37-cp37m-linux_x86_64.whl 19 | https://download.pytorch.org/whl/cpu/torchvision-0.9.1%2Bcpu-cp37-cp37m-linux_x86_64.whl 20 | omegaconf>=2.1.0.dev24 21 | hydra-core>=1.1.0.dev5 22 | scipy 23 | timm 24 | -------------------------------------------------------------------------------- /det/docs/tutorials/README.md: -------------------------------------------------------------------------------- 1 | # Read the docs: 2 | 3 | The latest documentation built from this directory is available at [detectron2.readthedocs.io](https://detectron2.readthedocs.io/). 4 | Documents in this directory are not meant to be read on github. 5 | -------------------------------------------------------------------------------- /det/docs/tutorials/builtin_datasets.md: -------------------------------------------------------------------------------- 1 | ../../datasets/README.md -------------------------------------------------------------------------------- /det/docs/tutorials/getting_started.md: -------------------------------------------------------------------------------- 1 | ../../GETTING_STARTED.md -------------------------------------------------------------------------------- /det/docs/tutorials/index.rst: -------------------------------------------------------------------------------- 1 | Tutorials 2 | ====================================== 3 | 4 | .. toctree:: 5 | :maxdepth: 2 6 | 7 | install 8 | getting_started 9 | builtin_datasets 10 | extend 11 | datasets 12 | data_loading 13 | augmentation 14 | models 15 | write-models 16 | training 17 | evaluation 18 | configs 19 | lazyconfigs 20 | deployment 21 | -------------------------------------------------------------------------------- /det/docs/tutorials/install.md: -------------------------------------------------------------------------------- 1 | ../../INSTALL.md -------------------------------------------------------------------------------- /det/projects/DeepLab/configs/Cityscapes-SemanticSegmentation/deeplab_v3_R_103_os16_mg124_poly_90k_bs16.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: Base-DeepLabV3-OS16-Semantic.yaml 2 | MODEL: 3 | WEIGHTS: "detectron2://DeepLab/R-103.pkl" 4 | PIXEL_MEAN: [123.675, 116.280, 103.530] 5 | PIXEL_STD: [58.395, 57.120, 57.375] 6 | BACKBONE: 7 | NAME: "build_resnet_deeplab_backbone" 8 | RESNETS: 9 | DEPTH: 101 10 | NORM: "SyncBN" 11 | RES5_MULTI_GRID: [1, 2, 4] 12 | STEM_TYPE: "deeplab" 13 | STEM_OUT_CHANNELS: 128 14 | STRIDE_IN_1X1: False 15 | SEM_SEG_HEAD: 16 | NAME: "DeepLabV3Head" 17 | NORM: "SyncBN" 18 | INPUT: 19 | FORMAT: "RGB" 20 | -------------------------------------------------------------------------------- /det/projects/DeepLab/configs/Cityscapes-SemanticSegmentation/deeplab_v3_plus_R_103_os16_mg124_poly_90k_bs16.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: Base-DeepLabV3-OS16-Semantic.yaml 2 | MODEL: 3 | WEIGHTS: "detectron2://DeepLab/R-103.pkl" 4 | PIXEL_MEAN: [123.675, 116.280, 103.530] 5 | PIXEL_STD: [58.395, 57.120, 57.375] 6 | BACKBONE: 7 | NAME: "build_resnet_deeplab_backbone" 8 | RESNETS: 9 | DEPTH: 101 10 | NORM: "SyncBN" 11 | OUT_FEATURES: ["res2", "res5"] 12 | RES5_MULTI_GRID: [1, 2, 4] 13 | STEM_TYPE: "deeplab" 14 | STEM_OUT_CHANNELS: 128 15 | STRIDE_IN_1X1: False 16 | SEM_SEG_HEAD: 17 | NAME: "DeepLabV3PlusHead" 18 | IN_FEATURES: ["res2", "res5"] 19 | PROJECT_FEATURES: ["res2"] 20 | PROJECT_CHANNELS: [48] 21 | NORM: "SyncBN" 22 | COMMON_STRIDE: 4 23 | INPUT: 24 | FORMAT: "RGB" 25 | -------------------------------------------------------------------------------- /det/projects/DeepLab/deeplab/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .build_solver import build_lr_scheduler 3 | from .config import add_deeplab_config 4 | from .resnet import build_resnet_deeplab_backbone 5 | from .semantic_seg import DeepLabV3Head, DeepLabV3PlusHead 6 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/HRNet/densepose_rcnn_HRFPN_HRNet_w32_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "https://1drv.ms/u/s!Aus8VCZ_C_33dYBMemi9xOUFR0w" 4 | BACKBONE: 5 | NAME: "build_hrfpn_backbone" 6 | RPN: 7 | IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5'] 8 | ROI_HEADS: 9 | IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5'] 10 | SOLVER: 11 | MAX_ITER: 130000 12 | STEPS: (100000, 120000) 13 | CLIP_GRADIENTS: 14 | ENABLED: True 15 | CLIP_TYPE: "norm" 16 | BASE_LR: 0.03 17 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/HRNet/densepose_rcnn_HRFPN_HRNet_w40_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "https://1drv.ms/u/s!Aus8VCZ_C_33ck0gvo5jfoWBOPo" 4 | BACKBONE: 5 | NAME: "build_hrfpn_backbone" 6 | RPN: 7 | IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5'] 8 | ROI_HEADS: 9 | IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5'] 10 | HRNET: 11 | STAGE2: 12 | NUM_CHANNELS: [40, 80] 13 | STAGE3: 14 | NUM_CHANNELS: [40, 80, 160] 15 | STAGE4: 16 | NUM_CHANNELS: [40, 80, 160, 320] 17 | SOLVER: 18 | MAX_ITER: 130000 19 | STEPS: (100000, 120000) 20 | CLIP_GRADIENTS: 21 | ENABLED: True 22 | CLIP_TYPE: "norm" 23 | BASE_LR: 0.03 24 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/HRNet/densepose_rcnn_HRFPN_HRNet_w48_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "https://1drv.ms/u/s!Aus8VCZ_C_33dKvqI6pBZlifgJk" 4 | BACKBONE: 5 | NAME: "build_hrfpn_backbone" 6 | RPN: 7 | IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5'] 8 | ROI_HEADS: 9 | IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5'] 10 | HRNET: 11 | STAGE2: 12 | NUM_CHANNELS: [48, 96] 13 | STAGE3: 14 | NUM_CHANNELS: [48, 96, 192] 15 | STAGE4: 16 | NUM_CHANNELS: [48, 96, 192, 384] 17 | SOLVER: 18 | MAX_ITER: 130000 19 | STEPS: (100000, 120000) 20 | CLIP_GRADIENTS: 21 | ENABLED: True 22 | CLIP_TYPE: "norm" 23 | BASE_LR: 0.03 24 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/cse/Base-DensePose-RCNN-FPN-Human.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | ROI_DENSEPOSE_HEAD: 4 | CSE: 5 | EMBEDDERS: 6 | "smpl_27554": 7 | TYPE: vertex_feature 8 | NUM_VERTICES: 27554 9 | FEATURE_DIM: 256 10 | FEATURES_TRAINABLE: False 11 | IS_TRAINABLE: True 12 | INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_smpl_27554_256.pkl" 13 | DATASETS: 14 | TRAIN: 15 | - "densepose_coco_2014_train_cse" 16 | - "densepose_coco_2014_valminusminival_cse" 17 | TEST: 18 | - "densepose_coco_2014_minival_cse" 19 | CLASS_TO_MESH_NAME_MAPPING: 20 | "0": "smpl_27554" 21 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/cse/densepose_rcnn_R_101_FPN_DL_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseDeepLabHead" 8 | CSE: 9 | EMBED_LOSS_NAME: "EmbeddingLoss" 10 | SOLVER: 11 | MAX_ITER: 130000 12 | STEPS: (100000, 120000) 13 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/cse/densepose_rcnn_R_101_FPN_DL_soft_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseDeepLabHead" 8 | CSE: 9 | EMBED_LOSS_NAME: "SoftEmbeddingLoss" 10 | SOLVER: 11 | MAX_ITER: 130000 12 | STEPS: (100000, 120000) 13 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/cse/densepose_rcnn_R_101_FPN_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseV1ConvXHead" 8 | CSE: 9 | EMBED_LOSS_NAME: "EmbeddingLoss" 10 | SOLVER: 11 | MAX_ITER: 130000 12 | STEPS: (100000, 120000) 13 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/cse/densepose_rcnn_R_101_FPN_soft_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseV1ConvXHead" 8 | CSE: 9 | EMBED_LOSS_NAME: "SoftEmbeddingLoss" 10 | SOLVER: 11 | MAX_ITER: 130000 12 | STEPS: (100000, 120000) 13 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/cse/densepose_rcnn_R_50_FPN_DL_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseDeepLabHead" 8 | CSE: 9 | EMBED_LOSS_NAME: "EmbeddingLoss" 10 | SOLVER: 11 | MAX_ITER: 130000 12 | STEPS: (100000, 120000) 13 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/cse/densepose_rcnn_R_50_FPN_DL_soft_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseDeepLabHead" 8 | CSE: 9 | EMBED_LOSS_NAME: "SoftEmbeddingLoss" 10 | SOLVER: 11 | MAX_ITER: 130000 12 | STEPS: (100000, 120000) 13 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/cse/densepose_rcnn_R_50_FPN_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseV1ConvXHead" 8 | CSE: 9 | EMBED_LOSS_NAME: "EmbeddingLoss" 10 | SOLVER: 11 | MAX_ITER: 130000 12 | STEPS: (100000, 120000) 13 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/cse/densepose_rcnn_R_50_FPN_soft_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseV1ConvXHead" 8 | CSE: 9 | EMBED_LOSS_NAME: "SoftEmbeddingLoss" 10 | SOLVER: 11 | MAX_ITER: 130000 12 | STEPS: (100000, 120000) 13 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_101_FPN_DL_WC1M_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseDeepLabHead" 8 | UV_CONFIDENCE: 9 | ENABLED: True 10 | TYPE: "iid_iso" 11 | SEGM_CONFIDENCE: 12 | ENABLED: True 13 | POINT_REGRESSION_WEIGHTS: 0.0005 14 | SOLVER: 15 | CLIP_GRADIENTS: 16 | ENABLED: True 17 | MAX_ITER: 130000 18 | STEPS: (100000, 120000) 19 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_101_FPN_DL_WC1_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseDeepLabHead" 8 | UV_CONFIDENCE: 9 | ENABLED: True 10 | TYPE: "iid_iso" 11 | POINT_REGRESSION_WEIGHTS: 0.0005 12 | SOLVER: 13 | CLIP_GRADIENTS: 14 | ENABLED: True 15 | MAX_ITER: 130000 16 | STEPS: (100000, 120000) 17 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_101_FPN_DL_WC2M_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseDeepLabHead" 8 | UV_CONFIDENCE: 9 | ENABLED: True 10 | TYPE: "indep_aniso" 11 | SEGM_CONFIDENCE: 12 | ENABLED: True 13 | POINT_REGRESSION_WEIGHTS: 0.0005 14 | SOLVER: 15 | CLIP_GRADIENTS: 16 | ENABLED: True 17 | MAX_ITER: 130000 18 | STEPS: (100000, 120000) 19 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_101_FPN_DL_WC2_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseDeepLabHead" 8 | UV_CONFIDENCE: 9 | ENABLED: True 10 | TYPE: "indep_aniso" 11 | POINT_REGRESSION_WEIGHTS: 0.0005 12 | SOLVER: 13 | CLIP_GRADIENTS: 14 | ENABLED: True 15 | MAX_ITER: 130000 16 | STEPS: (100000, 120000) 17 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_101_FPN_DL_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseDeepLabHead" 8 | SOLVER: 9 | MAX_ITER: 130000 10 | STEPS: (100000, 120000) 11 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_101_FPN_WC1M_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | ROI_DENSEPOSE_HEAD: 7 | UV_CONFIDENCE: 8 | ENABLED: True 9 | TYPE: "iid_iso" 10 | SEGM_CONFIDENCE: 11 | ENABLED: True 12 | POINT_REGRESSION_WEIGHTS: 0.0005 13 | SOLVER: 14 | CLIP_GRADIENTS: 15 | ENABLED: True 16 | MAX_ITER: 130000 17 | STEPS: (100000, 120000) 18 | WARMUP_FACTOR: 0.025 19 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_101_FPN_WC1_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | ROI_DENSEPOSE_HEAD: 7 | UV_CONFIDENCE: 8 | ENABLED: True 9 | TYPE: "iid_iso" 10 | POINT_REGRESSION_WEIGHTS: 0.0005 11 | SOLVER: 12 | CLIP_GRADIENTS: 13 | ENABLED: True 14 | MAX_ITER: 130000 15 | STEPS: (100000, 120000) 16 | WARMUP_FACTOR: 0.025 17 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_101_FPN_WC2M_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | ROI_DENSEPOSE_HEAD: 7 | UV_CONFIDENCE: 8 | ENABLED: True 9 | TYPE: "indep_aniso" 10 | SEGM_CONFIDENCE: 11 | ENABLED: True 12 | POINT_REGRESSION_WEIGHTS: 0.0005 13 | SOLVER: 14 | CLIP_GRADIENTS: 15 | ENABLED: True 16 | MAX_ITER: 130000 17 | STEPS: (100000, 120000) 18 | WARMUP_FACTOR: 0.025 19 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_101_FPN_WC2_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | ROI_DENSEPOSE_HEAD: 7 | UV_CONFIDENCE: 8 | ENABLED: True 9 | TYPE: "indep_aniso" 10 | POINT_REGRESSION_WEIGHTS: 0.0005 11 | SOLVER: 12 | CLIP_GRADIENTS: 13 | ENABLED: True 14 | MAX_ITER: 130000 15 | STEPS: (100000, 120000) 16 | WARMUP_FACTOR: 0.025 17 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_101_FPN_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | SOLVER: 7 | MAX_ITER: 130000 8 | STEPS: (100000, 120000) 9 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_101_FPN_s1x_legacy.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | RESNETS: 5 | DEPTH: 101 6 | ROI_DENSEPOSE_HEAD: 7 | NUM_COARSE_SEGM_CHANNELS: 15 8 | POOLER_RESOLUTION: 14 9 | HEATMAP_SIZE: 56 10 | INDEX_WEIGHTS: 2.0 11 | PART_WEIGHTS: 0.3 12 | POINT_REGRESSION_WEIGHTS: 0.1 13 | DECODER_ON: False 14 | SOLVER: 15 | BASE_LR: 0.002 16 | MAX_ITER: 130000 17 | STEPS: (100000, 120000) 18 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_50_FPN_DL_WC1M_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseDeepLabHead" 8 | UV_CONFIDENCE: 9 | ENABLED: True 10 | TYPE: "iid_iso" 11 | SEGM_CONFIDENCE: 12 | ENABLED: True 13 | POINT_REGRESSION_WEIGHTS: 0.0005 14 | SOLVER: 15 | CLIP_GRADIENTS: 16 | ENABLED: True 17 | MAX_ITER: 130000 18 | STEPS: (100000, 120000) 19 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_50_FPN_DL_WC1_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseDeepLabHead" 8 | UV_CONFIDENCE: 9 | ENABLED: True 10 | TYPE: "iid_iso" 11 | POINT_REGRESSION_WEIGHTS: 0.0005 12 | SOLVER: 13 | CLIP_GRADIENTS: 14 | ENABLED: True 15 | MAX_ITER: 130000 16 | STEPS: (100000, 120000) 17 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_50_FPN_DL_WC2M_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseDeepLabHead" 8 | UV_CONFIDENCE: 9 | ENABLED: True 10 | TYPE: "indep_aniso" 11 | SEGM_CONFIDENCE: 12 | ENABLED: True 13 | POINT_REGRESSION_WEIGHTS: 0.0005 14 | SOLVER: 15 | CLIP_GRADIENTS: 16 | ENABLED: True 17 | MAX_ITER: 130000 18 | STEPS: (100000, 120000) 19 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_50_FPN_DL_WC2_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseDeepLabHead" 8 | UV_CONFIDENCE: 9 | ENABLED: True 10 | TYPE: "indep_aniso" 11 | POINT_REGRESSION_WEIGHTS: 0.0005 12 | SOLVER: 13 | CLIP_GRADIENTS: 14 | ENABLED: True 15 | MAX_ITER: 130000 16 | STEPS: (100000, 120000) 17 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_50_FPN_DL_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | NAME: "DensePoseDeepLabHead" 8 | SOLVER: 9 | MAX_ITER: 130000 10 | STEPS: (100000, 120000) 11 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_50_FPN_WC1M_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | UV_CONFIDENCE: 8 | ENABLED: True 9 | TYPE: "iid_iso" 10 | SEGM_CONFIDENCE: 11 | ENABLED: True 12 | POINT_REGRESSION_WEIGHTS: 0.0005 13 | SOLVER: 14 | CLIP_GRADIENTS: 15 | ENABLED: True 16 | CLIP_TYPE: norm 17 | CLIP_VALUE: 100.0 18 | MAX_ITER: 130000 19 | STEPS: (100000, 120000) 20 | WARMUP_FACTOR: 0.025 21 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_50_FPN_WC1_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | UV_CONFIDENCE: 8 | ENABLED: True 9 | TYPE: "iid_iso" 10 | POINT_REGRESSION_WEIGHTS: 0.0005 11 | SOLVER: 12 | CLIP_GRADIENTS: 13 | ENABLED: True 14 | MAX_ITER: 130000 15 | STEPS: (100000, 120000) 16 | WARMUP_FACTOR: 0.025 17 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_50_FPN_WC2M_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | UV_CONFIDENCE: 8 | ENABLED: True 9 | TYPE: "indep_aniso" 10 | SEGM_CONFIDENCE: 11 | ENABLED: True 12 | POINT_REGRESSION_WEIGHTS: 0.0005 13 | SOLVER: 14 | CLIP_GRADIENTS: 15 | ENABLED: True 16 | MAX_ITER: 130000 17 | STEPS: (100000, 120000) 18 | WARMUP_FACTOR: 0.025 19 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_50_FPN_WC2_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | UV_CONFIDENCE: 8 | ENABLED: True 9 | TYPE: "indep_aniso" 10 | POINT_REGRESSION_WEIGHTS: 0.0005 11 | SOLVER: 12 | CLIP_GRADIENTS: 13 | ENABLED: True 14 | MAX_ITER: 130000 15 | STEPS: (100000, 120000) 16 | WARMUP_FACTOR: 0.025 17 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_50_FPN_s1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | SOLVER: 7 | MAX_ITER: 130000 8 | STEPS: (100000, 120000) 9 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/densepose_rcnn_R_50_FPN_s1x_legacy.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | NUM_COARSE_SEGM_CHANNELS: 15 8 | POOLER_RESOLUTION: 14 9 | HEATMAP_SIZE: 56 10 | INDEX_WEIGHTS: 2.0 11 | PART_WEIGHTS: 0.3 12 | POINT_REGRESSION_WEIGHTS: 0.1 13 | DECODER_ON: False 14 | SOLVER: 15 | BASE_LR: 0.002 16 | MAX_ITER: 130000 17 | STEPS: (100000, 120000) 18 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-RCNN-FPN-Atop10P_CA.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | DENSEPOSE_ON: True 7 | ROI_HEADS: 8 | NAME: "DensePoseROIHeads" 9 | IN_FEATURES: ["p2", "p3", "p4", "p5"] 10 | NUM_CLASSES: 1 11 | ROI_DENSEPOSE_HEAD: 12 | NAME: "DensePoseDeepLabHead" 13 | UV_CONFIDENCE: 14 | ENABLED: True 15 | TYPE: "iid_iso" 16 | SEGM_CONFIDENCE: 17 | ENABLED: True 18 | POINT_REGRESSION_WEIGHTS: 0.0005 19 | POOLER_TYPE: "ROIAlign" 20 | NUM_COARSE_SEGM_CHANNELS: 2 21 | COARSE_SEGM_TRAINED_BY_MASKS: True 22 | INDEX_WEIGHTS: 1.0 23 | SOLVER: 24 | CLIP_GRADIENTS: 25 | ENABLED: True 26 | WARMUP_FACTOR: 0.025 27 | MAX_ITER: 270000 28 | STEPS: (210000, 250000) 29 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/quick_schedules/cse/densepose_rcnn_R_50_FPN_DL_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../../cse/Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | ROI_DENSEPOSE_HEAD: 5 | NAME: "DensePoseDeepLabHead" 6 | DATASETS: 7 | TRAIN: ("densepose_coco_2014_minival_100_cse",) 8 | TEST: ("densepose_coco_2014_minival_100_cse",) 9 | SOLVER: 10 | MAX_ITER: 40 11 | STEPS: (30,) 12 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/quick_schedules/densepose_rcnn_HRFPN_HRNet_w32_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../HRNet/densepose_rcnn_HRFPN_HRNet_w32_s1x.yaml" 2 | DATASETS: 3 | TRAIN: ("densepose_coco_2014_minival_100",) 4 | TEST: ("densepose_coco_2014_minival_100",) 5 | SOLVER: 6 | MAX_ITER: 40 7 | STEPS: (30,) 8 | IMS_PER_BATCH: 2 9 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/quick_schedules/densepose_rcnn_R_50_FPN_DL_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | ROI_DENSEPOSE_HEAD: 5 | NAME: "DensePoseDeepLabHead" 6 | DATASETS: 7 | TRAIN: ("densepose_coco_2014_minival_100",) 8 | TEST: ("densepose_coco_2014_minival_100",) 9 | SOLVER: 10 | MAX_ITER: 40 11 | STEPS: (30,) 12 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/quick_schedules/densepose_rcnn_R_50_FPN_TTA_inference_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../densepose_rcnn_R_50_FPN_s1x.yaml" 2 | MODEL: 3 | WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/densepose_rcnn_R_50_FPN_s1x/165712039/model_final_162be9.pkl" 4 | DATASETS: 5 | TRAIN: () 6 | TEST: ("densepose_coco_2014_minival_100",) 7 | TEST: 8 | AUG: 9 | ENABLED: True 10 | MIN_SIZES: (400, 500, 600, 700, 800, 900, 1000, 1100, 1200) 11 | MAX_SIZE: 4000 12 | FLIP: True 13 | EXPECTED_RESULTS: [["bbox_TTA", "AP", 61.74, 0.03], ["densepose_gps_TTA", "AP", 60.22, 0.03], ["densepose_gpsm_TTA", "AP", 63.59, 0.03]] 14 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/quick_schedules/densepose_rcnn_R_50_FPN_WC1_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | UV_CONFIDENCE: 8 | ENABLED: True 9 | TYPE: "iid_iso" 10 | POINT_REGRESSION_WEIGHTS: 0.0005 11 | DATASETS: 12 | TRAIN: ("densepose_coco_2014_minival_100",) 13 | TEST: ("densepose_coco_2014_minival_100",) 14 | SOLVER: 15 | CLIP_GRADIENTS: 16 | ENABLED: True 17 | MAX_ITER: 40 18 | STEPS: (30,) 19 | WARMUP_FACTOR: 0.025 20 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/quick_schedules/densepose_rcnn_R_50_FPN_WC2_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_DENSEPOSE_HEAD: 7 | UV_CONFIDENCE: 8 | ENABLED: True 9 | TYPE: "indep_aniso" 10 | POINT_REGRESSION_WEIGHTS: 0.0005 11 | DATASETS: 12 | TRAIN: ("densepose_coco_2014_minival_100",) 13 | TEST: ("densepose_coco_2014_minival_100",) 14 | SOLVER: 15 | CLIP_GRADIENTS: 16 | ENABLED: True 17 | MAX_ITER: 40 18 | STEPS: (30,) 19 | WARMUP_FACTOR: 0.025 20 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/quick_schedules/densepose_rcnn_R_50_FPN_inference_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../densepose_rcnn_R_50_FPN_s1x.yaml" 2 | MODEL: 3 | WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/densepose_rcnn_R_50_FPN_s1x/165712039/model_final_162be9.pkl" 4 | DATASETS: 5 | TRAIN: () 6 | TEST: ("densepose_coco_2014_minival_100",) 7 | TEST: 8 | EXPECTED_RESULTS: [["bbox", "AP", 59.27, 0.025], ["densepose_gps", "AP", 60.11, 0.02], ["densepose_gpsm", "AP", 64.09, 0.02]] 9 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/quick_schedules/densepose_rcnn_R_50_FPN_instant_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | DATASETS: 5 | TRAIN: ("densepose_coco_2014_minival_100",) 6 | TEST: ("densepose_coco_2014_minival_100",) 7 | SOLVER: 8 | MAX_ITER: 40 9 | STEPS: (30,) 10 | -------------------------------------------------------------------------------- /det/projects/DensePose/configs/quick_schedules/densepose_rcnn_R_50_FPN_training_acc_test.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../Base-DensePose-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | ROI_HEADS: 5 | NUM_CLASSES: 1 6 | DATASETS: 7 | TRAIN: ("densepose_coco_2014_minival",) 8 | TEST: ("densepose_coco_2014_minival",) 9 | SOLVER: 10 | CLIP_GRADIENTS: 11 | ENABLED: True 12 | CLIP_TYPE: norm 13 | CLIP_VALUE: 1.0 14 | MAX_ITER: 6000 15 | STEPS: (5500, 5800) 16 | TEST: 17 | EXPECTED_RESULTS: [["bbox", "AP", 76.2477, 1.0], ["densepose_gps", "AP", 79.6090, 1.5], ["densepose_gpsm", "AP", 80.0061, 1.5]] 18 | 19 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .data.datasets import builtin # just to register data 3 | from .converters import builtin as builtin_converters # register converters 4 | from .config import ( 5 | add_densepose_config, 6 | add_densepose_head_config, 7 | add_hrnet_config, 8 | add_dataset_category_config, 9 | add_bootstrap_config, 10 | load_bootstrap_config, 11 | ) 12 | from .structures import DensePoseDataRelative, DensePoseList, DensePoseTransformData 13 | from .evaluation import DensePoseCOCOEvaluator 14 | from .modeling.roi_heads import DensePoseROIHeads 15 | from .modeling.test_time_augmentation import ( 16 | DensePoseGeneralizedRCNNWithTTA, 17 | DensePoseDatasetMapperTTA, 18 | ) 19 | from .utils.transform import load_from_cfg 20 | from .modeling.hrfpn import build_hrfpn_backbone 21 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/converters/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .hflip import HFlipConverter 4 | from .to_mask import ToMaskConverter 5 | from .to_chart_result import ToChartResultConverter, ToChartResultConverterWithConfidences 6 | from .segm_to_mask import ( 7 | predictor_output_with_fine_and_coarse_segm_to_mask, 8 | predictor_output_with_coarse_segm_to_mask, 9 | resample_fine_and_coarse_segm_to_bbox, 10 | ) 11 | from .chart_output_to_chart_result import ( 12 | densepose_chart_predictor_output_to_result, 13 | densepose_chart_predictor_output_to_result_with_confidences, 14 | ) 15 | from .chart_output_hflip import densepose_chart_predictor_output_hflip 16 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/data/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .meshes import builtin 4 | from .build import ( 5 | build_detection_test_loader, 6 | build_detection_train_loader, 7 | build_combined_loader, 8 | build_frame_selector, 9 | build_inference_based_loaders, 10 | has_inference_based_loaders, 11 | BootstrapDatasetFactoryCatalog, 12 | ) 13 | from .combined_loader import CombinedDataLoader 14 | from .dataset_mapper import DatasetMapper 15 | from .inference_based_loader import InferenceBasedLoader, ScoreBasedFilter 16 | from .image_list_dataset import ImageListDataset 17 | from .utils import is_relative_local_path, maybe_prepend_base_path 18 | 19 | # ensure the builtin datasets are registered 20 | from . import datasets 21 | 22 | # ensure the bootstrap datasets builders are registered 23 | from . import build 24 | 25 | __all__ = [k for k in globals().keys() if not k.startswith("_")] 26 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/data/datasets/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from . import builtin # ensure the builtin datasets are registered 4 | 5 | __all__ = [k for k in globals().keys() if "builtin" not in k and not k.startswith("_")] 6 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/data/datasets/builtin.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .chimpnsee import register_dataset as register_chimpnsee_dataset 3 | from .coco import BASE_DATASETS as BASE_COCO_DATASETS 4 | from .coco import DATASETS as COCO_DATASETS 5 | from .coco import register_datasets as register_coco_datasets 6 | from .lvis import DATASETS as LVIS_DATASETS 7 | from .lvis import register_datasets as register_lvis_datasets 8 | 9 | DEFAULT_DATASETS_ROOT = "datasets" 10 | 11 | 12 | register_coco_datasets(COCO_DATASETS, DEFAULT_DATASETS_ROOT) 13 | register_coco_datasets(BASE_COCO_DATASETS, DEFAULT_DATASETS_ROOT) 14 | register_lvis_datasets(LVIS_DATASETS, DEFAULT_DATASETS_ROOT) 15 | 16 | register_chimpnsee_dataset(DEFAULT_DATASETS_ROOT) # pyre-ignore[19] 17 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/data/datasets/dataset_type.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from enum import Enum 4 | 5 | 6 | class DatasetType(Enum): 7 | """ 8 | Dataset type, mostly used for datasets that contain data to bootstrap models on 9 | """ 10 | 11 | VIDEO_LIST = "video_list" 12 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/data/meshes/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved 2 | 3 | from . import builtin 4 | 5 | __all__ = [k for k in globals().keys() if "builtin" not in k and not k.startswith("_")] 6 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/data/samplers/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .densepose_uniform import DensePoseUniformSampler 4 | from .densepose_confidence_based import DensePoseConfidenceBasedSampler 5 | from .densepose_cse_uniform import DensePoseCSEUniformSampler 6 | from .densepose_cse_confidence_based import DensePoseCSEConfidenceBasedSampler 7 | from .mask_from_densepose import MaskFromDensePoseSampler 8 | from .prediction_to_gt import PredictionToGroundTruthSampler 9 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/data/samplers/densepose_cse_uniform.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .densepose_cse_base import DensePoseCSEBaseSampler 4 | from .densepose_uniform import DensePoseUniformSampler 5 | 6 | 7 | class DensePoseCSEUniformSampler(DensePoseCSEBaseSampler, DensePoseUniformSampler): 8 | """ 9 | Uniform Sampler for CSE 10 | """ 11 | 12 | pass 13 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/data/transform/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .image import ImageResizeTransform 4 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/data/video/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .frame_selector import ( 4 | FrameSelectionStrategy, 5 | RandomKFramesSelector, 6 | FirstKFramesSelector, 7 | LastKFramesSelector, 8 | FrameTsList, 9 | FrameSelector, 10 | ) 11 | 12 | from .video_keyframe_dataset import ( 13 | VideoKeyframeDataset, 14 | video_list_from_file, 15 | list_keyframes, 16 | read_keyframes, 17 | ) 18 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/engine/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .trainer import Trainer 4 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/evaluation/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .evaluator import DensePoseCOCOEvaluator 4 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/modeling/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .confidence import DensePoseConfidenceModelConfig, DensePoseUVConfidenceType 4 | from .filter import DensePoseDataFilter 5 | from .inference import densepose_inference 6 | from .utils import initialize_module_params 7 | from .build import ( 8 | build_densepose_data_filter, 9 | build_densepose_embedder, 10 | build_densepose_head, 11 | build_densepose_losses, 12 | build_densepose_predictor, 13 | ) 14 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/modeling/cse/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved 2 | 3 | from .vertex_direct_embedder import VertexDirectEmbedder 4 | from .vertex_feature_embedder import VertexFeatureEmbedder 5 | from .embedder import Embedder 6 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/modeling/losses/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .chart import DensePoseChartLoss 4 | from .chart_with_confidences import DensePoseChartWithConfidenceLoss 5 | from .cse import DensePoseCseLoss 6 | from .registry import DENSEPOSE_LOSS_REGISTRY 7 | 8 | 9 | __all__ = [ 10 | "DensePoseChartLoss", 11 | "DensePoseChartWithConfidenceLoss", 12 | "DensePoseCseLoss", 13 | "DENSEPOSE_LOSS_REGISTRY", 14 | ] 15 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/modeling/losses/registry.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from detectron2.utils.registry import Registry 4 | 5 | DENSEPOSE_LOSS_REGISTRY = Registry("DENSEPOSE_LOSS") 6 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/modeling/predictors/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .chart import DensePoseChartPredictor 4 | from .chart_confidence import DensePoseChartConfidencePredictorMixin 5 | from .chart_with_confidence import DensePoseChartWithConfidencePredictor 6 | from .cse import DensePoseEmbeddingPredictor 7 | from .cse_confidence import DensePoseEmbeddingConfidencePredictorMixin 8 | from .cse_with_confidence import DensePoseEmbeddingWithConfidencePredictor 9 | from .registry import DENSEPOSE_PREDICTOR_REGISTRY 10 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/modeling/predictors/chart_with_confidence.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from . import DensePoseChartConfidencePredictorMixin, DensePoseChartPredictor 4 | from .registry import DENSEPOSE_PREDICTOR_REGISTRY 5 | 6 | 7 | @DENSEPOSE_PREDICTOR_REGISTRY.register() 8 | class DensePoseChartWithConfidencePredictor( 9 | DensePoseChartConfidencePredictorMixin, DensePoseChartPredictor 10 | ): 11 | """ 12 | Predictor that combines chart and chart confidence estimation 13 | """ 14 | 15 | pass 16 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/modeling/predictors/cse_with_confidence.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from . import DensePoseEmbeddingConfidencePredictorMixin, DensePoseEmbeddingPredictor 4 | from .registry import DENSEPOSE_PREDICTOR_REGISTRY 5 | 6 | 7 | @DENSEPOSE_PREDICTOR_REGISTRY.register() 8 | class DensePoseEmbeddingWithConfidencePredictor( 9 | DensePoseEmbeddingConfidencePredictorMixin, DensePoseEmbeddingPredictor 10 | ): 11 | """ 12 | Predictor that combines CSE and CSE confidence estimation 13 | """ 14 | 15 | pass 16 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/modeling/predictors/registry.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from detectron2.utils.registry import Registry 4 | 5 | DENSEPOSE_PREDICTOR_REGISTRY = Registry("DENSEPOSE_PREDICTOR") 6 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/modeling/roi_heads/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .v1convx import DensePoseV1ConvXHead 4 | from .deeplab import DensePoseDeepLabHead 5 | from .registry import ROI_DENSEPOSE_HEAD_REGISTRY 6 | from .roi_head import Decoder, DensePoseROIHeads 7 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/modeling/roi_heads/registry.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from detectron2.utils.registry import Registry 4 | 5 | ROI_DENSEPOSE_HEAD_REGISTRY = Registry("ROI_DENSEPOSE_HEAD") 6 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/modeling/utils.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from torch import nn 4 | 5 | 6 | def initialize_module_params(module: nn.Module) -> None: 7 | for name, param in module.named_parameters(): 8 | if "bias" in name: 9 | nn.init.constant_(param, 0) 10 | elif "weight" in name: 11 | nn.init.kaiming_normal_(param, mode="fan_out", nonlinearity="relu") 12 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/structures/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | from .chart import DensePoseChartPredictorOutput 4 | from .chart_confidence import decorate_predictor_output_class_with_confidences 5 | from .cse_confidence import decorate_cse_predictor_output_class_with_confidences 6 | from .chart_result import ( 7 | DensePoseChartResult, 8 | DensePoseChartResultWithConfidences, 9 | quantize_densepose_chart_result, 10 | compress_quantized_densepose_chart_result, 11 | decompress_compressed_densepose_chart_result, 12 | ) 13 | from .cse import DensePoseEmbeddingPredictorOutput 14 | from .data_relative import DensePoseDataRelative 15 | from .list import DensePoseList 16 | from .mesh import Mesh, create_mesh 17 | from .transform_data import DensePoseTransformData, normalized_coords_transform 18 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/det/projects/DensePose/densepose/utils/__init__.py -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/utils/logger.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | import logging 3 | 4 | 5 | def verbosity_to_level(verbosity) -> int: 6 | if verbosity is not None: 7 | if verbosity == 0: 8 | return logging.WARNING 9 | elif verbosity == 1: 10 | return logging.INFO 11 | elif verbosity >= 2: 12 | return logging.DEBUG 13 | return logging.WARNING 14 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/utils/transform.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from detectron2.data import MetadataCatalog 3 | from detectron2.utils.file_io import PathManager 4 | 5 | from densepose import DensePoseTransformData 6 | 7 | 8 | def load_for_dataset(dataset_name): 9 | path = MetadataCatalog.get(dataset_name).densepose_transform_src 10 | densepose_transform_data_fpath = PathManager.get_local_path(path) 11 | return DensePoseTransformData.load(densepose_transform_data_fpath) 12 | 13 | 14 | def load_from_cfg(cfg): 15 | return load_for_dataset(cfg.DATASETS.TEST[0]) 16 | -------------------------------------------------------------------------------- /det/projects/DensePose/densepose/vis/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/det/projects/DensePose/densepose/vis/__init__.py -------------------------------------------------------------------------------- /det/projects/DensePose/dev/README.md: -------------------------------------------------------------------------------- 1 | 2 | ## Some scripts for developers to use, include: 3 | 4 | - `run_instant_tests.sh`: run training for a few iterations. 5 | - `run_inference_tests.sh`: run inference on a small dataset. 6 | - `../../dev/linter.sh`: lint the codebase before commit 7 | - `../../dev/parse_results.sh`: parse results from log file. 8 | -------------------------------------------------------------------------------- /det/projects/DensePose/doc/RELEASE_2020_04.md: -------------------------------------------------------------------------------- 1 | # DensePose Confidence Estimation and Model Zoo Improvements 2 | 3 | * [DensePose models with confidence estimation](doc/DENSEPOSE_IUV.md#ModelZooConfidence) 4 | * [Panoptic FPN and DeepLabV3 head implementation](doc/DENSEPOSE_IUV.md#ModelZooDeepLabV3) 5 | * Test time augmentations for DensePose 6 | * New evaluation metric (GPSm) that yields more reliable scores 7 | -------------------------------------------------------------------------------- /det/projects/DensePose/tests/test_image_resize_transform.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | import unittest 4 | import torch 5 | 6 | from densepose.data.transform import ImageResizeTransform 7 | 8 | 9 | class TestImageResizeTransform(unittest.TestCase): 10 | def test_image_resize_1(self): 11 | images_batch = torch.ones((3, 3, 100, 100), dtype=torch.uint8) * 100 12 | transform = ImageResizeTransform() 13 | images_transformed = transform(images_batch) 14 | IMAGES_GT = torch.ones((3, 3, 800, 800), dtype=torch.float) * 100 15 | self.assertEqual(images_transformed.size(), IMAGES_GT.size()) 16 | self.assertAlmostEqual(torch.abs(IMAGES_GT - images_transformed).max().item(), 0.0) 17 | -------------------------------------------------------------------------------- /det/projects/MViTv2/configs/cascade_mask_rcnn_mvitv2_b_3x.py: -------------------------------------------------------------------------------- 1 | from .cascade_mask_rcnn_mvitv2_t_3x import model, dataloader, optimizer, lr_multiplier, train 2 | 3 | 4 | model.backbone.bottom_up.depth = 24 5 | model.backbone.bottom_up.last_block_indexes = (1, 4, 20, 23) 6 | model.backbone.bottom_up.drop_path_rate = 0.4 7 | 8 | train.init_checkpoint = "detectron2://ImageNetPretrained/mvitv2/MViTv2_B_in1k.pyth" 9 | -------------------------------------------------------------------------------- /det/projects/MViTv2/configs/cascade_mask_rcnn_mvitv2_b_in21k_3x.py: -------------------------------------------------------------------------------- 1 | from .cascade_mask_rcnn_mvitv2_b_3x import model, dataloader, optimizer, lr_multiplier, train 2 | 3 | train.init_checkpoint = "detectron2://ImageNetPretrained/mvitv2/MViTv2_B_in21k.pyth" 4 | -------------------------------------------------------------------------------- /det/projects/MViTv2/configs/cascade_mask_rcnn_mvitv2_h_in21k_lsj_3x.py: -------------------------------------------------------------------------------- 1 | from .cascade_mask_rcnn_mvitv2_b_3x import model, optimizer, train, lr_multiplier 2 | from .common.coco_loader_lsj import dataloader 3 | 4 | 5 | model.backbone.bottom_up.embed_dim = 192 6 | model.backbone.bottom_up.depth = 80 7 | model.backbone.bottom_up.num_heads = 3 8 | model.backbone.bottom_up.last_block_indexes = (3, 11, 71, 79) 9 | model.backbone.bottom_up.drop_path_rate = 0.6 10 | model.backbone.bottom_up.use_act_checkpoint = True 11 | 12 | train.init_checkpoint = "detectron2://ImageNetPretrained/mvitv2/MViTv2_H_in21k.pyth" 13 | -------------------------------------------------------------------------------- /det/projects/MViTv2/configs/cascade_mask_rcnn_mvitv2_s_3x.py: -------------------------------------------------------------------------------- 1 | from .cascade_mask_rcnn_mvitv2_t_3x import model, dataloader, optimizer, lr_multiplier, train 2 | 3 | 4 | model.backbone.bottom_up.depth = 16 5 | model.backbone.bottom_up.last_block_indexes = (0, 2, 13, 15) 6 | 7 | train.init_checkpoint = "detectron2://ImageNetPretrained/mvitv2/MViTv2_S_in1k.pyth" 8 | -------------------------------------------------------------------------------- /det/projects/MViTv2/configs/common/coco_loader_lsj.py: -------------------------------------------------------------------------------- 1 | import detectron2.data.transforms as T 2 | from detectron2 import model_zoo 3 | from detectron2.config import LazyCall as L 4 | 5 | from .coco_loader import dataloader 6 | 7 | # Data using LSJ 8 | image_size = 1024 9 | dataloader.train.mapper.augmentations = [ 10 | L(T.RandomFlip)(horizontal=True), # flip first 11 | L(T.ResizeScale)( 12 | min_scale=0.1, max_scale=2.0, target_height=image_size, target_width=image_size 13 | ), 14 | L(T.FixedSizeCrop)(crop_size=(image_size, image_size)), 15 | ] 16 | dataloader.train.mapper.image_format = "RGB" 17 | dataloader.train.total_batch_size = 64 18 | # recompute boxes due to cropping 19 | dataloader.train.mapper.recompute_boxes = True 20 | -------------------------------------------------------------------------------- /det/projects/Panoptic-DeepLab/configs/Cityscapes-PanopticSegmentation/panoptic_deeplab_R_52_os16_mg124_poly_90k_bs32_crop_512_1024.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: Base-PanopticDeepLab-OS16.yaml 2 | MODEL: 3 | WEIGHTS: "detectron2://DeepLab/R-52.pkl" 4 | PIXEL_MEAN: [123.675, 116.280, 103.530] 5 | PIXEL_STD: [58.395, 57.120, 57.375] 6 | BACKBONE: 7 | NAME: "build_resnet_deeplab_backbone" 8 | RESNETS: 9 | DEPTH: 50 10 | NORM: "SyncBN" 11 | RES5_MULTI_GRID: [1, 2, 4] 12 | STEM_TYPE: "deeplab" 13 | STEM_OUT_CHANNELS: 128 14 | STRIDE_IN_1X1: False 15 | SOLVER: 16 | MAX_ITER: 90000 17 | INPUT: 18 | FORMAT: "RGB" 19 | CROP: 20 | SIZE: (512, 1024) 21 | -------------------------------------------------------------------------------- /det/projects/Panoptic-DeepLab/configs/Cityscapes-PanopticSegmentation/panoptic_deeplab_R_52_os16_mg124_poly_90k_bs32_crop_512_1024_dsconv.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: Base-PanopticDeepLab-OS16.yaml 2 | MODEL: 3 | WEIGHTS: "detectron2://DeepLab/R-52.pkl" 4 | PIXEL_MEAN: [123.675, 116.280, 103.530] 5 | PIXEL_STD: [58.395, 57.120, 57.375] 6 | BACKBONE: 7 | NAME: "build_resnet_deeplab_backbone" 8 | RESNETS: 9 | DEPTH: 50 10 | NORM: "SyncBN" 11 | RES5_MULTI_GRID: [1, 2, 4] 12 | STEM_TYPE: "deeplab" 13 | STEM_OUT_CHANNELS: 128 14 | STRIDE_IN_1X1: False 15 | PANOPTIC_DEEPLAB: 16 | USE_DEPTHWISE_SEPARABLE_CONV: True 17 | SEM_SEG_HEAD: 18 | USE_DEPTHWISE_SEPARABLE_CONV: True 19 | SOLVER: 20 | MAX_ITER: 90000 21 | INPUT: 22 | FORMAT: "RGB" 23 | CROP: 24 | SIZE: (512, 1024) 25 | -------------------------------------------------------------------------------- /det/projects/Panoptic-DeepLab/panoptic_deeplab/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .config import add_panoptic_deeplab_config 3 | from .dataset_mapper import PanopticDeeplabDatasetMapper 4 | from .panoptic_seg import ( 5 | PanopticDeepLab, 6 | INS_EMBED_BRANCHES_REGISTRY, 7 | build_ins_embed_branch, 8 | PanopticDeepLabSemSegHead, 9 | PanopticDeepLabInsEmbedHead, 10 | ) 11 | -------------------------------------------------------------------------------- /det/projects/PointRend/configs/InstanceSegmentation/Base-Implicit-PointRend.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../../../../configs/Base-RCNN-FPN.yaml" 2 | MODEL: 3 | MASK_ON: true 4 | ROI_MASK_HEAD: 5 | NAME: "ImplicitPointRendMaskHead" 6 | POOLER_TYPE: "" # No RoI pooling, let the head process image features directly 7 | FC_DIM: 1024 8 | NUM_FC: 2 9 | POINT_HEAD: 10 | NAME: "ImplicitPointHead" 11 | FC_DIM: 256 12 | NUM_FC: 3 13 | IN_FEATURES: ["p2"] 14 | NUM_CLASSES: 80 15 | CLS_AGNOSTIC_MASK: False 16 | TRAIN_NUM_POINTS: 196 17 | SUBDIVISION_STEPS: 3 18 | SUBDIVISION_NUM_POINTS: 784 19 | IMPLICIT_POINTREND: 20 | IMAGE_FEATURE_ENABLED: True 21 | POS_ENC_ENABLED: True 22 | PARAMS_L2_REGULARIZER: 0.00001 23 | INPUT: 24 | # PointRend for instance segmentation does not work with "polygon" mask_format. 25 | MASK_FORMAT: "bitmask" 26 | -------------------------------------------------------------------------------- /det/projects/PointRend/configs/InstanceSegmentation/Base-PointRend-RCNN-FPN.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../../../../configs/Base-RCNN-FPN.yaml" 2 | MODEL: 3 | MASK_ON: true 4 | ROI_BOX_HEAD: 5 | TRAIN_ON_PRED_BOXES: True 6 | ROI_MASK_HEAD: 7 | POOLER_TYPE: "" # No RoI pooling, let the head process image features directly 8 | NAME: "PointRendMaskHead" 9 | FC_DIM: 1024 10 | NUM_FC: 2 11 | OUTPUT_SIDE_RESOLUTION: 7 12 | IN_FEATURES: ["p2"] # for the coarse mask head 13 | POINT_HEAD_ON: True 14 | POINT_HEAD: 15 | FC_DIM: 256 16 | NUM_FC: 3 17 | IN_FEATURES: ["p2"] 18 | INPUT: 19 | # PointRend for instance segmentation does not work with "polygon" mask_format. 20 | MASK_FORMAT: "bitmask" 21 | -------------------------------------------------------------------------------- /det/projects/PointRend/configs/InstanceSegmentation/implicit_pointrend_R_50_FPN_1x_coco.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-Implicit-PointRend.yaml" 2 | MODEL: 3 | WEIGHTS: detectron2://ImageNetPretrained/MSRA/R-50.pkl 4 | RESNETS: 5 | DEPTH: 50 6 | # To add COCO AP evaluation against the higher-quality LVIS annotations. 7 | # DATASETS: 8 | # TEST: ("coco_2017_val", "lvis_v0.5_val_cocofied") 9 | -------------------------------------------------------------------------------- /det/projects/PointRend/configs/InstanceSegmentation/implicit_pointrend_R_50_FPN_3x_coco.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-Implicit-PointRend.yaml" 2 | MODEL: 3 | WEIGHTS: detectron2://ImageNetPretrained/MSRA/R-50.pkl 4 | RESNETS: 5 | DEPTH: 50 6 | SOLVER: 7 | STEPS: (210000, 250000) 8 | MAX_ITER: 270000 9 | # To add COCO AP evaluation against the higher-quality LVIS annotations. 10 | # DATASETS: 11 | # TEST: ("coco_2017_val", "lvis_v0.5_val_cocofied") 12 | -------------------------------------------------------------------------------- /det/projects/PointRend/configs/InstanceSegmentation/pointrend_rcnn_R_101_FPN_3x_coco.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: Base-PointRend-RCNN-FPN.yaml 2 | MODEL: 3 | WEIGHTS: detectron2://ImageNetPretrained/MSRA/R-101.pkl 4 | MASK_ON: true 5 | RESNETS: 6 | DEPTH: 101 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | # To add COCO AP evaluation against the higher-quality LVIS annotations. 11 | # DATASETS: 12 | # TEST: ("coco_2017_val", "lvis_v0.5_val_cocofied") 13 | -------------------------------------------------------------------------------- /det/projects/PointRend/configs/InstanceSegmentation/pointrend_rcnn_R_50_FPN_1x_cityscapes.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: Base-PointRend-RCNN-FPN.yaml 2 | MODEL: 3 | WEIGHTS: detectron2://ImageNetPretrained/MSRA/R-50.pkl 4 | RESNETS: 5 | DEPTH: 50 6 | ROI_HEADS: 7 | NUM_CLASSES: 8 8 | POINT_HEAD: 9 | NUM_CLASSES: 8 10 | DATASETS: 11 | TEST: ("cityscapes_fine_instance_seg_val",) 12 | TRAIN: ("cityscapes_fine_instance_seg_train",) 13 | SOLVER: 14 | BASE_LR: 0.01 15 | IMS_PER_BATCH: 8 16 | MAX_ITER: 24000 17 | STEPS: (18000,) 18 | INPUT: 19 | MAX_SIZE_TEST: 2048 20 | MAX_SIZE_TRAIN: 2048 21 | MIN_SIZE_TEST: 1024 22 | MIN_SIZE_TRAIN: (800, 832, 864, 896, 928, 960, 992, 1024) 23 | -------------------------------------------------------------------------------- /det/projects/PointRend/configs/InstanceSegmentation/pointrend_rcnn_R_50_FPN_1x_coco.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: Base-PointRend-RCNN-FPN.yaml 2 | MODEL: 3 | WEIGHTS: detectron2://ImageNetPretrained/MSRA/R-50.pkl 4 | RESNETS: 5 | DEPTH: 50 6 | # To add COCO AP evaluation against the higher-quality LVIS annotations. 7 | # DATASETS: 8 | # TEST: ("coco_2017_val", "lvis_v0.5_val_cocofied") 9 | -------------------------------------------------------------------------------- /det/projects/PointRend/configs/InstanceSegmentation/pointrend_rcnn_R_50_FPN_3x_coco.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: Base-PointRend-RCNN-FPN.yaml 2 | MODEL: 3 | WEIGHTS: detectron2://ImageNetPretrained/MSRA/R-50.pkl 4 | RESNETS: 5 | DEPTH: 50 6 | SOLVER: 7 | STEPS: (210000, 250000) 8 | MAX_ITER: 270000 9 | # To add COCO AP evaluation against the higher-quality LVIS annotations. 10 | # DATASETS: 11 | # TEST: ("coco_2017_val", "lvis_v0.5_val_cocofied") 12 | 13 | -------------------------------------------------------------------------------- /det/projects/PointRend/configs/InstanceSegmentation/pointrend_rcnn_X_101_32x8d_FPN_3x_coco.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: Base-PointRend-RCNN-FPN.yaml 2 | MODEL: 3 | MASK_ON: True 4 | WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl" 5 | PIXEL_STD: [57.375, 57.120, 58.395] 6 | RESNETS: 7 | STRIDE_IN_1X1: False # this is a C2 model 8 | NUM_GROUPS: 32 9 | WIDTH_PER_GROUP: 8 10 | DEPTH: 101 11 | SOLVER: 12 | STEPS: (210000, 250000) 13 | MAX_ITER: 270000 14 | # To add COCO AP evaluation against the higher-quality LVIS annotations. 15 | # DATASETS: 16 | # TEST: ("coco_2017_val", "lvis_v0.5_val_cocofied") 17 | -------------------------------------------------------------------------------- /det/projects/PointRend/configs/SemanticSegmentation/Base-PointRend-Semantic-FPN.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../../../../configs/Base-RCNN-FPN.yaml" 2 | MODEL: 3 | META_ARCHITECTURE: "SemanticSegmentor" 4 | BACKBONE: 5 | FREEZE_AT: 0 6 | SEM_SEG_HEAD: 7 | NAME: "PointRendSemSegHead" 8 | POINT_HEAD: 9 | NUM_CLASSES: 54 10 | FC_DIM: 256 11 | NUM_FC: 3 12 | IN_FEATURES: ["p2"] 13 | TRAIN_NUM_POINTS: 1024 14 | SUBDIVISION_STEPS: 2 15 | SUBDIVISION_NUM_POINTS: 8192 16 | COARSE_SEM_SEG_HEAD_NAME: "SemSegFPNHead" 17 | COARSE_PRED_EACH_LAYER: False 18 | DATASETS: 19 | TRAIN: ("coco_2017_train_panoptic_stuffonly",) 20 | TEST: ("coco_2017_val_panoptic_stuffonly",) 21 | -------------------------------------------------------------------------------- /det/projects/PointRend/configs/SemanticSegmentation/pointrend_semantic_R_101_FPN_1x_cityscapes.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: Base-PointRend-Semantic-FPN.yaml 2 | MODEL: 3 | WEIGHTS: detectron2://ImageNetPretrained/MSRA/R-101.pkl 4 | RESNETS: 5 | DEPTH: 101 6 | SEM_SEG_HEAD: 7 | NUM_CLASSES: 19 8 | POINT_HEAD: 9 | NUM_CLASSES: 19 10 | TRAIN_NUM_POINTS: 2048 11 | SUBDIVISION_NUM_POINTS: 8192 12 | DATASETS: 13 | TRAIN: ("cityscapes_fine_sem_seg_train",) 14 | TEST: ("cityscapes_fine_sem_seg_val",) 15 | SOLVER: 16 | BASE_LR: 0.01 17 | STEPS: (40000, 55000) 18 | MAX_ITER: 65000 19 | IMS_PER_BATCH: 32 20 | INPUT: 21 | MIN_SIZE_TRAIN: (512, 768, 1024, 1280, 1536, 1792, 2048) 22 | MIN_SIZE_TRAIN_SAMPLING: "choice" 23 | MIN_SIZE_TEST: 1024 24 | MAX_SIZE_TRAIN: 4096 25 | MAX_SIZE_TEST: 2048 26 | CROP: 27 | ENABLED: True 28 | TYPE: "absolute" 29 | SIZE: (512, 1024) 30 | SINGLE_CATEGORY_MAX_AREA: 0.75 31 | COLOR_AUG_SSD: True 32 | DATALOADER: 33 | NUM_WORKERS: 10 34 | -------------------------------------------------------------------------------- /det/projects/PointRend/point_rend/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .config import add_pointrend_config 3 | from .mask_head import PointRendMaskHead, ImplicitPointRendMaskHead 4 | from .semantic_seg import PointRendSemSegHead 5 | from .color_augmentation import ColorAugSSDTransform 6 | 7 | from . import roi_heads as _ # only registration 8 | -------------------------------------------------------------------------------- /det/projects/PointSup/configs/implicit_pointrend_R_50_FPN_3x_point_sup_point_aug_coco.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../../PointRend/configs/InstanceSegmentation/implicit_pointrend_R_50_FPN_3x_coco.yaml" 2 | MODEL: 3 | ROI_MASK_HEAD: 4 | NAME: "ImplicitPointRendPointSupHead" 5 | INPUT: 6 | POINT_SUP: True 7 | SAMPLE_POINTS: 5 8 | DATASETS: 9 | TRAIN: ("coco_2017_train_points_n10_v1_without_masks",) 10 | -------------------------------------------------------------------------------- /det/projects/PointSup/configs/mask_rcnn_R_50_FPN_3x_point_sup_coco.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "../../../configs/Base-RCNN-FPN.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: True 5 | RESNETS: 6 | DEPTH: 50 7 | ROI_MASK_HEAD: 8 | NAME: "MaskRCNNConvUpsamplePointSupHead" 9 | INPUT: 10 | POINT_SUP: True 11 | DATASETS: 12 | TRAIN: ("coco_2017_train_points_n10_v1_without_masks",) 13 | SOLVER: 14 | STEPS: (210000, 250000) 15 | MAX_ITER: 270000 16 | -------------------------------------------------------------------------------- /det/projects/PointSup/configs/mask_rcnn_R_50_FPN_3x_point_sup_point_aug_coco.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "mask_rcnn_R_50_FPN_3x_point_sup_coco.yaml" 2 | INPUT: 3 | SAMPLE_POINTS: 5 4 | -------------------------------------------------------------------------------- /det/projects/PointSup/point_sup/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved 2 | from . import register_point_annotations 3 | from .config import add_point_sup_config 4 | from .dataset_mapper import PointSupDatasetMapper 5 | from .mask_head import MaskRCNNConvUpsamplePointSupHead 6 | from .point_utils import get_point_coords_from_point_annotation 7 | -------------------------------------------------------------------------------- /det/projects/PointSup/point_sup/config.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved 3 | 4 | 5 | def add_point_sup_config(cfg): 6 | """ 7 | Add config for point supervision. 8 | """ 9 | # Use point annotation 10 | cfg.INPUT.POINT_SUP = False 11 | # Sample only part of points in each iteration. 12 | # Default: 0, use all available points. 13 | cfg.INPUT.SAMPLE_POINTS = 0 14 | -------------------------------------------------------------------------------- /det/projects/Rethinking-BatchNorm/configs/mask_rcnn_BNhead.py: -------------------------------------------------------------------------------- 1 | from detectron2.model_zoo import get_config 2 | 3 | model = get_config("common/models/mask_rcnn_fpn.py").model 4 | 5 | model.backbone.bottom_up.freeze_at = 2 6 | 7 | model.roi_heads.box_head.conv_norm = model.roi_heads.mask_head.conv_norm = "BN" 8 | # 4conv1fc head 9 | model.roi_heads.box_head.conv_dims = [256, 256, 256, 256] 10 | model.roi_heads.box_head.fc_dims = [1024] 11 | 12 | dataloader = get_config("common/data/coco.py").dataloader 13 | lr_multiplier = get_config("common/coco_schedule.py").lr_multiplier_3x 14 | optimizer = get_config("common/optim.py").SGD 15 | train = get_config("common/train.py").train 16 | 17 | train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 18 | train.max_iter = 270000 # 3x for batchsize = 16 19 | -------------------------------------------------------------------------------- /det/projects/Rethinking-BatchNorm/configs/mask_rcnn_BNhead_batch_stats.py: -------------------------------------------------------------------------------- 1 | from torch.nn import BatchNorm2d 2 | from torch.nn import functional as F 3 | 4 | 5 | class BatchNormBatchStat(BatchNorm2d): 6 | """ 7 | BN that uses batch stat in inference 8 | """ 9 | 10 | def forward(self, input): 11 | if self.training: 12 | return super().forward(input) 13 | return F.batch_norm(input, None, None, self.weight, self.bias, True, 1.0, self.eps) 14 | 15 | 16 | # After training with the base config, it's sufficient to load its model with 17 | # this config only for inference -- because the training-time behavior is identical. 18 | from .mask_rcnn_BNhead import model, dataloader, lr_multiplier, optimizer, train 19 | 20 | model.roi_heads.box_head.conv_norm = model.roi_heads.mask_head.conv_norm = BatchNormBatchStat 21 | -------------------------------------------------------------------------------- /det/projects/Rethinking-BatchNorm/configs/mask_rcnn_SyncBNhead.py: -------------------------------------------------------------------------------- 1 | from .mask_rcnn_BNhead import model, dataloader, lr_multiplier, optimizer, train 2 | 3 | model.roi_heads.box_head.conv_norm = model.roi_heads.mask_head.conv_norm = "SyncBN" 4 | -------------------------------------------------------------------------------- /det/projects/Rethinking-BatchNorm/configs/retinanet_SyncBNhead.py: -------------------------------------------------------------------------------- 1 | from detectron2.model_zoo import get_config 2 | from torch import nn 3 | 4 | model = get_config("common/models/retinanet.py").model 5 | model.backbone.bottom_up.freeze_at = 2 6 | 7 | # The head will overwrite string "SyncBN" to use domain-specific BN, so we 8 | # provide a class here to use shared BN in training. 9 | model.head.norm = nn.SyncBatchNorm2d 10 | 11 | dataloader = get_config("common/data/coco.py").dataloader 12 | lr_multiplier = get_config("common/coco_schedule.py").lr_multiplier_3x 13 | optimizer = get_config("common/optim.py").SGD 14 | train = get_config("common/train.py").train 15 | 16 | optimizer.lr = 0.01 17 | 18 | train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 19 | train.max_iter = 270000 # 3x for batchsize = 16 20 | -------------------------------------------------------------------------------- /det/projects/TensorMask/configs/Base-TensorMask.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "TensorMask" 3 | MASK_ON: True 4 | BACKBONE: 5 | NAME: "build_retinanet_resnet_fpn_backbone" 6 | RESNETS: 7 | OUT_FEATURES: ["res2", "res3", "res4", "res5"] 8 | ANCHOR_GENERATOR: 9 | SIZES: [[44, 60], [88, 120], [176, 240], [352, 480], [704, 960], [1408, 1920]] 10 | ASPECT_RATIOS: [[1.0]] 11 | FPN: 12 | IN_FEATURES: ["res2", "res3", "res4", "res5"] 13 | FUSE_TYPE: "avg" 14 | TENSOR_MASK: 15 | ALIGNED_ON: True 16 | BIPYRAMID_ON: True 17 | DATASETS: 18 | TRAIN: ("coco_2017_train",) 19 | TEST: ("coco_2017_val",) 20 | SOLVER: 21 | IMS_PER_BATCH: 16 22 | BASE_LR: 0.02 23 | STEPS: (60000, 80000) 24 | MAX_ITER: 90000 25 | VERSION: 2 26 | -------------------------------------------------------------------------------- /det/projects/TensorMask/configs/tensormask_R_50_FPN_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-TensorMask.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | -------------------------------------------------------------------------------- /det/projects/TensorMask/configs/tensormask_R_50_FPN_6x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-TensorMask.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | RESNETS: 5 | DEPTH: 50 6 | SOLVER: 7 | STEPS: (480000, 520000) 8 | MAX_ITER: 540000 9 | INPUT: 10 | MIN_SIZE_TRAIN_SAMPLING: "range" 11 | MIN_SIZE_TRAIN: (640, 800) 12 | -------------------------------------------------------------------------------- /det/projects/TensorMask/tensormask/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .config import add_tensormask_config 3 | from .arch import TensorMask 4 | -------------------------------------------------------------------------------- /det/projects/TensorMask/tensormask/layers/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .swap_align2nat import SwapAlign2Nat, swap_align2nat 3 | 4 | __all__ = [k for k in globals().keys() if not k.startswith("_")] 5 | -------------------------------------------------------------------------------- /det/projects/TensorMask/tensormask/layers/csrc/vision.cpp: -------------------------------------------------------------------------------- 1 | // Copyright (c) Facebook, Inc. and its affiliates. 2 | 3 | #include 4 | #include "SwapAlign2Nat/SwapAlign2Nat.h" 5 | 6 | namespace tensormask { 7 | 8 | PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) { 9 | m.def( 10 | "swap_align2nat_forward", 11 | &SwapAlign2Nat_forward, 12 | "SwapAlign2Nat_forward"); 13 | m.def( 14 | "swap_align2nat_backward", 15 | &SwapAlign2Nat_backward, 16 | "SwapAlign2Nat_backward"); 17 | } 18 | 19 | } // namespace tensormask 20 | -------------------------------------------------------------------------------- /det/projects/TensorMask/tests/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | -------------------------------------------------------------------------------- /det/projects/TridentNet/configs/Base-TridentNet-Fast-C4.yaml: -------------------------------------------------------------------------------- 1 | MODEL: 2 | META_ARCHITECTURE: "GeneralizedRCNN" 3 | BACKBONE: 4 | NAME: "build_trident_resnet_backbone" 5 | ROI_HEADS: 6 | NAME: "TridentRes5ROIHeads" 7 | POSITIVE_FRACTION: 0.5 8 | BATCH_SIZE_PER_IMAGE: 128 9 | PROPOSAL_APPEND_GT: False 10 | PROPOSAL_GENERATOR: 11 | NAME: "TridentRPN" 12 | RPN: 13 | POST_NMS_TOPK_TRAIN: 500 14 | TRIDENT: 15 | NUM_BRANCH: 3 16 | BRANCH_DILATIONS: [1, 2, 3] 17 | TEST_BRANCH_IDX: 1 18 | TRIDENT_STAGE: "res4" 19 | DATASETS: 20 | TRAIN: ("coco_2017_train",) 21 | TEST: ("coco_2017_val",) 22 | SOLVER: 23 | IMS_PER_BATCH: 16 24 | BASE_LR: 0.02 25 | STEPS: (60000, 80000) 26 | MAX_ITER: 90000 27 | INPUT: 28 | MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) 29 | VERSION: 2 30 | -------------------------------------------------------------------------------- /det/projects/TridentNet/configs/tridentnet_fast_R_101_C4_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-TridentNet-Fast-C4.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 101 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | -------------------------------------------------------------------------------- /det/projects/TridentNet/configs/tridentnet_fast_R_50_C4_1x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-TridentNet-Fast-C4.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 50 7 | -------------------------------------------------------------------------------- /det/projects/TridentNet/configs/tridentnet_fast_R_50_C4_3x.yaml: -------------------------------------------------------------------------------- 1 | _BASE_: "Base-TridentNet-Fast-C4.yaml" 2 | MODEL: 3 | WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl" 4 | MASK_ON: False 5 | RESNETS: 6 | DEPTH: 50 7 | SOLVER: 8 | STEPS: (210000, 250000) 9 | MAX_ITER: 270000 10 | -------------------------------------------------------------------------------- /det/projects/TridentNet/tridentnet/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from .config import add_tridentnet_config 3 | from .trident_backbone import ( 4 | TridentBottleneckBlock, 5 | build_trident_resnet_backbone, 6 | make_trident_stage, 7 | ) 8 | from .trident_rpn import TridentRPN 9 | from .trident_rcnn import TridentRes5ROIHeads, TridentStandardROIHeads 10 | -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/COCO/cascade_mask_rcnn_mvitv2_l_in21k_50ep.py: -------------------------------------------------------------------------------- 1 | from .cascade_mask_rcnn_mvitv2_b_in21k_100ep import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | train, 6 | optimizer, 7 | ) 8 | 9 | model.backbone.bottom_up.embed_dim = 144 10 | model.backbone.bottom_up.depth = 48 11 | model.backbone.bottom_up.num_heads = 2 12 | model.backbone.bottom_up.last_block_indexes = (1, 7, 43, 47) 13 | model.backbone.bottom_up.drop_path_rate = 0.5 14 | 15 | 16 | train.init_checkpoint = "detectron2://ImageNetPretrained/mvitv2/MViTv2_L_in21k.pyth" 17 | 18 | train.max_iter = train.max_iter // 2 # 100ep -> 50ep 19 | lr_multiplier.scheduler.milestones = [ 20 | milestone // 2 for milestone in lr_multiplier.scheduler.milestones 21 | ] 22 | lr_multiplier.scheduler.num_updates = train.max_iter 23 | -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/COCO/cascade_mask_rcnn_swin_l_in21k_50ep.py: -------------------------------------------------------------------------------- 1 | from .cascade_mask_rcnn_swin_b_in21k_50ep import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | train, 6 | optimizer, 7 | ) 8 | 9 | model.backbone.bottom_up.depths = [2, 2, 18, 2] 10 | model.backbone.bottom_up.drop_path_rate = 0.4 11 | model.backbone.bottom_up.embed_dim = 192 12 | model.backbone.bottom_up.num_heads = [6, 12, 24, 48] 13 | 14 | 15 | train.init_checkpoint = "detectron2://ImageNetPretrained/swin/swin_large_patch4_window7_224_22k.pth" 16 | -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/COCO/cascade_mask_rcnn_vimdet_s_100ep.py: -------------------------------------------------------------------------------- 1 | from functools import partial 2 | 3 | from .cascade_mask_rcnn_vimdet_b_100ep import ( 4 | dataloader, 5 | lr_multiplier, 6 | model, 7 | train, 8 | optimizer, 9 | get_vim_lr_decay_rate, 10 | ) 11 | 12 | train.init_checkpoint = "" 13 | 14 | model.backbone.net.embed_dim = 384 15 | model.backbone.net.depth = 24 16 | model.backbone.net.if_cls_token = True 17 | model.backbone.net.pretrained = "/share/project/lianghuizhu/JudgeLM-Project/old_ckpts/VisionProjects/deit/output/a-vim-weights/bc_vim_s_79p8acc.pth" 18 | optimizer.params.lr_factor_func = partial(get_vim_lr_decay_rate, num_layers=24, lr_decay_rate=0.837) -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/COCO/cascade_mask_rcnn_vimdet_t_100ep.py: -------------------------------------------------------------------------------- 1 | from functools import partial 2 | 3 | from .cascade_mask_rcnn_vimdet_b_100ep import ( 4 | dataloader, 5 | lr_multiplier, 6 | model, 7 | train, 8 | optimizer, 9 | get_vim_lr_decay_rate, 10 | ) 11 | 12 | train.init_checkpoint = "" 13 | 14 | model.backbone.net.embed_dim = 192 15 | model.backbone.net.depth = 24 16 | model.backbone.net.pretrained = "/share/project/lianghuizhu/JudgeLM-Project/old_ckpts/VisionProjects/deit/output/vim_tiny_patch16_224_bimambav2_final_pool_mean_abs_pos_embed_rope_also_residual/best_checkpoint.pth" -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/COCO/cascade_mask_rcnn_vimdet_t_100ep_adj1.py: -------------------------------------------------------------------------------- 1 | from functools import partial 2 | 3 | from .cascade_mask_rcnn_vimdet_b_100ep import ( 4 | dataloader, 5 | lr_multiplier, 6 | model, 7 | train, 8 | optimizer, 9 | get_vim_lr_decay_rate, 10 | ) 11 | 12 | train.init_checkpoint = "" 13 | 14 | model.backbone.net.embed_dim = 192 15 | model.backbone.net.depth = 24 16 | model.backbone.net.pretrained = "/mnt/bn/lianghuidata/Vim/det/ckpts/best_checkpoint.pth" 17 | optimizer.params.lr_factor_func = partial(get_vim_lr_decay_rate, num_layers=24, lr_decay_rate=0.837) -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/COCO/cascade_mask_rcnn_vitdet_l_100ep.py: -------------------------------------------------------------------------------- 1 | from functools import partial 2 | 3 | from .cascade_mask_rcnn_vitdet_b_100ep import ( 4 | dataloader, 5 | lr_multiplier, 6 | model, 7 | train, 8 | optimizer, 9 | get_vit_lr_decay_rate, 10 | ) 11 | 12 | train.init_checkpoint = ( 13 | "detectron2://ImageNetPretrained/MAE/mae_pretrain_vit_large.pth?matching_heuristics=True" 14 | ) 15 | 16 | model.backbone.net.embed_dim = 1024 17 | model.backbone.net.depth = 24 18 | model.backbone.net.num_heads = 16 19 | model.backbone.net.drop_path_rate = 0.4 20 | # 5, 11, 17, 23 for global attention 21 | model.backbone.net.window_block_indexes = ( 22 | list(range(0, 5)) + list(range(6, 11)) + list(range(12, 17)) + list(range(18, 23)) 23 | ) 24 | 25 | optimizer.params.lr_factor_func = partial(get_vit_lr_decay_rate, lr_decay_rate=0.8, num_layers=24) 26 | -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/COCO/cascade_mask_rcnn_vitdet_s_100ep.py: -------------------------------------------------------------------------------- 1 | from functools import partial 2 | 3 | from .cascade_mask_rcnn_vitdet_b_100ep import ( 4 | dataloader, 5 | lr_multiplier, 6 | model, 7 | train, 8 | optimizer, 9 | get_vit_lr_decay_rate, 10 | ) 11 | 12 | train.init_checkpoint = "/share/project/lianghuizhu/JudgeLM-Project/old_ckpts/VisionProjects/deit/output/a-deit-weights/deit_small_patch16_224-cd65a155.pth" 13 | 14 | model.backbone.net.embed_dim = 384 15 | model.backbone.net.depth = 12 16 | model.backbone.net.num_heads = 6 17 | model.backbone.net.use_rel_pos = False 18 | -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/COCO/cascade_mask_rcnn_vitdet_t_100ep.py: -------------------------------------------------------------------------------- 1 | from functools import partial 2 | 3 | from .cascade_mask_rcnn_vitdet_b_100ep import ( 4 | dataloader, 5 | lr_multiplier, 6 | model, 7 | train, 8 | optimizer, 9 | get_vit_lr_decay_rate, 10 | ) 11 | 12 | train.init_checkpoint = "/share/project/lianghuizhu/JudgeLM-Project/old_ckpts/VisionProjects/deit/output/deit-t/best_checkpoint.pth" 13 | 14 | model.backbone.net.embed_dim = 192 15 | model.backbone.net.depth = 12 16 | model.backbone.net.num_heads = 3 17 | model.backbone.net.use_rel_pos = False 18 | -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/COCO/mask_rcnn_vitdet_l_100ep.py: -------------------------------------------------------------------------------- 1 | from functools import partial 2 | 3 | from .mask_rcnn_vitdet_b_100ep import ( 4 | dataloader, 5 | lr_multiplier, 6 | model, 7 | train, 8 | optimizer, 9 | get_vit_lr_decay_rate, 10 | ) 11 | 12 | train.init_checkpoint = ( 13 | "detectron2://ImageNetPretrained/MAE/mae_pretrain_vit_large.pth?matching_heuristics=True" 14 | ) 15 | 16 | model.backbone.net.embed_dim = 1024 17 | model.backbone.net.depth = 24 18 | model.backbone.net.num_heads = 16 19 | model.backbone.net.drop_path_rate = 0.4 20 | # 5, 11, 17, 23 for global attention 21 | model.backbone.net.window_block_indexes = ( 22 | list(range(0, 5)) + list(range(6, 11)) + list(range(12, 17)) + list(range(18, 23)) 23 | ) 24 | 25 | optimizer.params.lr_factor_func = partial(get_vit_lr_decay_rate, lr_decay_rate=0.8, num_layers=24) 26 | -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/COCO/mask_rcnn_vitdet_t_100ep.py: -------------------------------------------------------------------------------- 1 | from functools import partial 2 | 3 | from .mask_rcnn_vitdet_b_100ep import ( 4 | dataloader, 5 | lr_multiplier, 6 | model, 7 | train, 8 | optimizer, 9 | get_vit_lr_decay_rate, 10 | ) 11 | 12 | train.init_checkpoint = "/share/project/lianghuizhu/JudgeLM-Project/old_ckpts/VisionProjects/deit/output/deit-t/best_checkpoint.pth" 13 | 14 | model.backbone.net.embed_dim = 192 15 | model.backbone.net.depth = 12 16 | model.backbone.net.num_heads = 3 17 | 18 | -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/LVIS/cascade_mask_rcnn_mvitv2_h_in21k_50ep.py: -------------------------------------------------------------------------------- 1 | from .cascade_mask_rcnn_mvitv2_b_in21k_100ep import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | train, 6 | optimizer, 7 | ) 8 | 9 | model.backbone.bottom_up.embed_dim = 192 10 | model.backbone.bottom_up.depth = 80 11 | model.backbone.bottom_up.num_heads = 3 12 | model.backbone.bottom_up.last_block_indexes = (3, 11, 71, 79) 13 | model.backbone.bottom_up.drop_path_rate = 0.6 14 | model.backbone.bottom_up.use_act_checkpoint = True 15 | 16 | train.init_checkpoint = "detectron2://ImageNetPretrained/mvitv2/MViTv2_H_in21k.pyth" 17 | 18 | train.max_iter = train.max_iter // 2 # 100ep -> 50ep 19 | lr_multiplier.scheduler.milestones = [ 20 | milestone // 2 for milestone in lr_multiplier.scheduler.milestones 21 | ] 22 | lr_multiplier.scheduler.num_updates = train.max_iter 23 | lr_multiplier.warmup_length = 250 / train.max_iter 24 | 25 | optimizer.lr = 2e-5 26 | -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/LVIS/cascade_mask_rcnn_mvitv2_l_in21k_50ep.py: -------------------------------------------------------------------------------- 1 | from .cascade_mask_rcnn_mvitv2_b_in21k_100ep import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | train, 6 | optimizer, 7 | ) 8 | 9 | model.backbone.bottom_up.embed_dim = 144 10 | model.backbone.bottom_up.depth = 48 11 | model.backbone.bottom_up.num_heads = 2 12 | model.backbone.bottom_up.last_block_indexes = (1, 7, 43, 47) 13 | model.backbone.bottom_up.drop_path_rate = 0.5 14 | 15 | train.init_checkpoint = "detectron2://ImageNetPretrained/mvitv2/MViTv2_L_in21k.pyth" 16 | 17 | train.max_iter = train.max_iter // 2 # 100ep -> 50ep 18 | lr_multiplier.scheduler.milestones = [ 19 | milestone // 2 for milestone in lr_multiplier.scheduler.milestones 20 | ] 21 | lr_multiplier.scheduler.num_updates = train.max_iter 22 | lr_multiplier.warmup_length = 250 / train.max_iter 23 | 24 | optimizer.lr = 4e-5 25 | -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/LVIS/cascade_mask_rcnn_swin_l_in21k_50ep.py: -------------------------------------------------------------------------------- 1 | from .cascade_mask_rcnn_swin_b_in21k_50ep import ( 2 | dataloader, 3 | lr_multiplier, 4 | model, 5 | train, 6 | optimizer, 7 | ) 8 | 9 | model.backbone.bottom_up.embed_dim = 192 10 | model.backbone.bottom_up.num_heads = [6, 12, 24, 48] 11 | 12 | train.init_checkpoint = "detectron2://ImageNetPretrained/swin/swin_large_patch4_window7_224_22k.pth" 13 | -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/LVIS/mask_rcnn_vitdet_l_100ep.py: -------------------------------------------------------------------------------- 1 | from functools import partial 2 | 3 | from detectron2.modeling.backbone.vit import get_vit_lr_decay_rate 4 | 5 | from .mask_rcnn_vitdet_b_100ep import ( 6 | dataloader, 7 | lr_multiplier, 8 | model, 9 | train, 10 | optimizer, 11 | ) 12 | 13 | train.init_checkpoint = ( 14 | "detectron2://ImageNetPretrained/MAE/mae_pretrain_vit_large.pth?matching_heuristics=True" 15 | ) 16 | 17 | model.backbone.net.embed_dim = 1024 18 | model.backbone.net.depth = 24 19 | model.backbone.net.num_heads = 16 20 | model.backbone.net.drop_path_rate = 0.4 21 | # 5, 11, 17, 23 for global attention 22 | model.backbone.net.window_block_indexes = ( 23 | list(range(0, 5)) + list(range(6, 11)) + list(range(12, 17)) + list(range(18, 23)) 24 | ) 25 | 26 | optimizer.params.lr_factor_func = partial(get_vit_lr_decay_rate, lr_decay_rate=0.8, num_layers=24) 27 | -------------------------------------------------------------------------------- /det/projects/ViTDet/configs/common/coco_loader_lsj.py: -------------------------------------------------------------------------------- 1 | import detectron2.data.transforms as T 2 | from detectron2 import model_zoo 3 | from detectron2.config import LazyCall as L 4 | 5 | # Data using LSJ 6 | image_size = 1024 7 | dataloader = model_zoo.get_config("common/data/coco.py").dataloader 8 | dataloader.train.mapper.augmentations = [ 9 | L(T.RandomFlip)(horizontal=True), # flip first 10 | L(T.ResizeScale)( 11 | min_scale=0.1, max_scale=2.0, target_height=image_size, target_width=image_size 12 | ), 13 | L(T.FixedSizeCrop)(crop_size=(image_size, image_size), pad=False), 14 | ] 15 | dataloader.train.mapper.image_format = "RGB" 16 | dataloader.train.total_batch_size = 64 17 | # recompute boxes due to cropping 18 | dataloader.train.mapper.recompute_boxes = True 19 | 20 | dataloader.test.mapper.augmentations = [ 21 | L(T.ResizeShortestEdge)(short_edge_length=image_size, max_size=image_size), 22 | ] 23 | -------------------------------------------------------------------------------- /det/scripts/eval_vim_tiny_vimdet.sh: -------------------------------------------------------------------------------- 1 | python3 tools/lazyconfig_train_net.py \ 2 | --config-file /mnt/bn/lianghuidata/Vim/det/projects/ViTDet/configs/COCO/cascade_mask_rcnn_vimdet_t_100ep_adj1.py \ 3 | --eval-only train.init_checkpoint="/mnt/bn/lianghuidata/Vim/det/released_ckpt/vimdet.pth" -------------------------------------------------------------------------------- /det/scripts/ft_vim_tiny_vimdet.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # bash /client-tools/repair_A100.sh 3 | source /mnt/bn/lianghuidata/miniconda/bin/activate /mnt/bn/lianghuidata/miniconda/envs/det2 4 | cd /mnt/bn/lianghuidata/Vim/det; 5 | 6 | DET_CONFIG_NAME=cascade_mask_rcnn_vimdet_t_100ep_adj1 7 | DET_CONFIG=projects/ViTDet/configs/COCO/$DET_CONFIG_NAME.py 8 | 9 | 10 | /mnt/bn/lianghuidata/miniconda/envs/det2/bin/python3 tools/lazyconfig_train_net.py \ 11 | --num-gpus 4 --num-machines 1 --machine-rank 0 --dist-url "tcp://127.13.44.12:60900" \ 12 | --config-file ${DET_CONFIG} \ 13 | train.output_dir=/mnt/bn/lianghuidata/Vim/det/work_dirs/$DET_CONFIG_NAME-4gpu-test-env \ 14 | dataloader.train.num_workers=128 \ 15 | dataloader.test.num_workers=8 -------------------------------------------------------------------------------- /det/tests/README.md: -------------------------------------------------------------------------------- 1 | ## Unit Tests 2 | 3 | To run the unittests, do: 4 | ``` 5 | cd detectron2 6 | python -m unittest discover -v -s ./tests 7 | ``` 8 | 9 | There are also end-to-end inference & training tests, in [dev/run_*_tests.sh](../dev). 10 | -------------------------------------------------------------------------------- /det/tests/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | -------------------------------------------------------------------------------- /det/tests/config/dir1/bad_import.py: -------------------------------------------------------------------------------- 1 | # import from directory is not allowed 2 | from . import dir1a 3 | -------------------------------------------------------------------------------- /det/tests/config/dir1/bad_import2.py: -------------------------------------------------------------------------------- 1 | from .does_not_exist import x 2 | -------------------------------------------------------------------------------- /det/tests/config/dir1/dir1_a.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | dir1a_str = "base_a_1" 3 | dir1a_dict = {"a": 1, "b": 2} 4 | -------------------------------------------------------------------------------- /det/tests/config/dir1/dir1_b.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from detectron2.config import LazyConfig 3 | 4 | # equivalent to relative import 5 | dir1a_str, dir1a_dict = LazyConfig.load_rel("dir1_a.py", ("dir1a_str", "dir1a_dict")) 6 | 7 | dir1b_str = dir1a_str + "_from_b" 8 | dir1b_dict = dir1a_dict 9 | 10 | # Every import is a reload: not modified by other config files 11 | assert dir1a_dict.a == 1 12 | -------------------------------------------------------------------------------- /det/tests/config/dir1/load_rel.py: -------------------------------------------------------------------------------- 1 | # test that load_rel can work 2 | from detectron2.config import LazyConfig 3 | 4 | x = LazyConfig.load_rel("dir1_a.py", "dir1a_dict") 5 | assert x["a"] == 1 6 | -------------------------------------------------------------------------------- /det/tests/config/root_cfg.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | from itertools import count 3 | 4 | from detectron2.config import LazyCall as L 5 | 6 | from .dir1.dir1_a import dir1a_dict, dir1a_str 7 | 8 | dir1a_dict.a = "modified" 9 | 10 | # modification above won't affect future imports 11 | from .dir1.dir1_b import dir1b_dict, dir1b_str 12 | 13 | 14 | lazyobj = L(count)(x=dir1a_str, y=dir1b_str) 15 | -------------------------------------------------------------------------------- /det/tests/data/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/det/tests/data/__init__.py -------------------------------------------------------------------------------- /det/tests/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/det/tests/layers/__init__.py -------------------------------------------------------------------------------- /det/tests/modeling/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/det/tests/modeling/__init__.py -------------------------------------------------------------------------------- /det/tests/structures/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/det/tests/structures/__init__.py -------------------------------------------------------------------------------- /det/tests/structures/test_keypoints.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | import unittest 3 | import torch 4 | 5 | from detectron2.structures.keypoints import Keypoints 6 | 7 | 8 | class TestKeypoints(unittest.TestCase): 9 | def test_cat_keypoints(self): 10 | keypoints1 = Keypoints(torch.rand(2, 21, 3)) 11 | keypoints2 = Keypoints(torch.rand(4, 21, 3)) 12 | 13 | cat_keypoints = keypoints1.cat([keypoints1, keypoints2]) 14 | self.assertTrue(torch.all(cat_keypoints.tensor[:2] == keypoints1.tensor).item()) 15 | self.assertTrue(torch.all(cat_keypoints.tensor[2:] == keypoints2.tensor).item()) 16 | 17 | 18 | if __name__ == "__main__": 19 | unittest.main() 20 | -------------------------------------------------------------------------------- /det/tests/test_packaging.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | import unittest 3 | 4 | from detectron2.utils.collect_env import collect_env_info 5 | 6 | 7 | class TestProjects(unittest.TestCase): 8 | def test_import(self): 9 | from detectron2.projects import point_rend 10 | 11 | _ = point_rend.add_pointrend_config 12 | 13 | import detectron2.projects.deeplab as deeplab 14 | 15 | _ = deeplab.add_deeplab_config 16 | 17 | # import detectron2.projects.panoptic_deeplab as panoptic_deeplab 18 | 19 | # _ = panoptic_deeplab.add_panoptic_deeplab_config 20 | 21 | 22 | class TestCollectEnv(unittest.TestCase): 23 | def test(self): 24 | _ = collect_env_info() 25 | -------------------------------------------------------------------------------- /det/tests/tracking/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/det/tests/tracking/__init__.py -------------------------------------------------------------------------------- /det/tests/utils/test_tensorboardx.py: -------------------------------------------------------------------------------- 1 | import os 2 | import tempfile 3 | import unittest 4 | 5 | from detectron2.utils.events import TensorboardXWriter 6 | 7 | 8 | # TODO Fix up capitalization 9 | class TestTensorboardXWriter(unittest.TestCase): 10 | def test_no_files_created(self) -> None: 11 | with tempfile.TemporaryDirectory() as tmp_dir: 12 | writer = TensorboardXWriter(tmp_dir) 13 | writer.close() 14 | 15 | self.assertFalse(os.listdir(tmp_dir)) 16 | 17 | def test_single_write(self) -> None: 18 | with tempfile.TemporaryDirectory() as tmp_dir: 19 | writer = TensorboardXWriter(tmp_dir) 20 | writer._writer.add_scalar("testing", 1, 1) 21 | writer.close() 22 | 23 | self.assertTrue(os.listdir(tmp_dir)) 24 | -------------------------------------------------------------------------------- /det/tools/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/det/tools/__init__.py -------------------------------------------------------------------------------- /det/tools/deploy/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. 2 | # See https://pytorch.org/tutorials/advanced/cpp_frontend.html 3 | cmake_minimum_required(VERSION 3.12 FATAL_ERROR) 4 | project(torchscript_mask_rcnn) 5 | 6 | find_package(Torch REQUIRED) 7 | find_package(OpenCV REQUIRED) 8 | find_package(TorchVision REQUIRED) # needed by export-method=tracing/scripting 9 | 10 | add_executable(torchscript_mask_rcnn torchscript_mask_rcnn.cpp) 11 | target_link_libraries( 12 | torchscript_mask_rcnn 13 | -Wl,--no-as-needed TorchVision::TorchVision -Wl,--as-needed 14 | "${TORCH_LIBRARIES}" ${OpenCV_LIBS}) 15 | set_property(TARGET torchscript_mask_rcnn PROPERTY CXX_STANDARD 14) 16 | -------------------------------------------------------------------------------- /mamba-1p1p1/.gitignore: -------------------------------------------------------------------------------- 1 | *__pycache__/ 2 | *.egg-info/ 3 | build/ 4 | **.so 5 | -------------------------------------------------------------------------------- /mamba-1p1p1/.gitmodules: -------------------------------------------------------------------------------- 1 | [submodule "3rdparty/lm-evaluation-harness"] 2 | path = 3rdparty/lm-evaluation-harness 3 | url = https://github.com/EleutherAI/lm-evaluation-harness/ 4 | -------------------------------------------------------------------------------- /mamba-1p1p1/AUTHORS: -------------------------------------------------------------------------------- 1 | Tri Dao, tri@tridao.me 2 | Albert Gu, agu@andrew.cmu.edu 3 | -------------------------------------------------------------------------------- /mamba-1p1p1/assets/selection.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/mamba-1p1p1/assets/selection.png -------------------------------------------------------------------------------- /mamba-1p1p1/csrc/selective_scan/selective_scan_bwd_bf16_complex.cu: -------------------------------------------------------------------------------- 1 | /****************************************************************************** 2 | * Copyright (c) 2023, Tri Dao. 3 | ******************************************************************************/ 4 | 5 | // Split into multiple files to compile in paralell 6 | 7 | #include "selective_scan_bwd_kernel.cuh" 8 | 9 | template void selective_scan_bwd_cuda(SSMParamsBwd ¶ms, cudaStream_t stream); -------------------------------------------------------------------------------- /mamba-1p1p1/csrc/selective_scan/selective_scan_bwd_bf16_real.cu: -------------------------------------------------------------------------------- 1 | /****************************************************************************** 2 | * Copyright (c) 2023, Tri Dao. 3 | ******************************************************************************/ 4 | 5 | // Split into multiple files to compile in paralell 6 | 7 | #include "selective_scan_bwd_kernel.cuh" 8 | 9 | template void selective_scan_bwd_cuda(SSMParamsBwd ¶ms, cudaStream_t stream); -------------------------------------------------------------------------------- /mamba-1p1p1/csrc/selective_scan/selective_scan_bwd_fp16_complex.cu: -------------------------------------------------------------------------------- 1 | /****************************************************************************** 2 | * Copyright (c) 2023, Tri Dao. 3 | ******************************************************************************/ 4 | 5 | // Split into multiple files to compile in paralell 6 | 7 | #include "selective_scan_bwd_kernel.cuh" 8 | 9 | template void selective_scan_bwd_cuda(SSMParamsBwd ¶ms, cudaStream_t stream); -------------------------------------------------------------------------------- /mamba-1p1p1/csrc/selective_scan/selective_scan_bwd_fp16_real.cu: -------------------------------------------------------------------------------- 1 | /****************************************************************************** 2 | * Copyright (c) 2023, Tri Dao. 3 | ******************************************************************************/ 4 | 5 | // Split into multiple files to compile in paralell 6 | 7 | #include "selective_scan_bwd_kernel.cuh" 8 | 9 | template void selective_scan_bwd_cuda(SSMParamsBwd ¶ms, cudaStream_t stream); -------------------------------------------------------------------------------- /mamba-1p1p1/csrc/selective_scan/selective_scan_bwd_fp32_complex.cu: -------------------------------------------------------------------------------- 1 | /****************************************************************************** 2 | * Copyright (c) 2023, Tri Dao. 3 | ******************************************************************************/ 4 | 5 | // Split into multiple files to compile in paralell 6 | 7 | #include "selective_scan_bwd_kernel.cuh" 8 | 9 | template void selective_scan_bwd_cuda(SSMParamsBwd ¶ms, cudaStream_t stream); -------------------------------------------------------------------------------- /mamba-1p1p1/csrc/selective_scan/selective_scan_bwd_fp32_real.cu: -------------------------------------------------------------------------------- 1 | /****************************************************************************** 2 | * Copyright (c) 2023, Tri Dao. 3 | ******************************************************************************/ 4 | 5 | // Split into multiple files to compile in paralell 6 | 7 | #include "selective_scan_bwd_kernel.cuh" 8 | 9 | template void selective_scan_bwd_cuda(SSMParamsBwd ¶ms, cudaStream_t stream); -------------------------------------------------------------------------------- /mamba-1p1p1/csrc/selective_scan/selective_scan_fwd_bf16.cu: -------------------------------------------------------------------------------- 1 | /****************************************************************************** 2 | * Copyright (c) 2023, Tri Dao. 3 | ******************************************************************************/ 4 | 5 | // Split into multiple files to compile in paralell 6 | 7 | #include "selective_scan_fwd_kernel.cuh" 8 | 9 | template void selective_scan_fwd_cuda(SSMParamsBase ¶ms, cudaStream_t stream); 10 | template void selective_scan_fwd_cuda(SSMParamsBase ¶ms, cudaStream_t stream); -------------------------------------------------------------------------------- /mamba-1p1p1/csrc/selective_scan/selective_scan_fwd_fp16.cu: -------------------------------------------------------------------------------- 1 | /****************************************************************************** 2 | * Copyright (c) 2023, Tri Dao. 3 | ******************************************************************************/ 4 | 5 | // Split into multiple files to compile in paralell 6 | 7 | #include "selective_scan_fwd_kernel.cuh" 8 | 9 | template void selective_scan_fwd_cuda(SSMParamsBase ¶ms, cudaStream_t stream); 10 | template void selective_scan_fwd_cuda(SSMParamsBase ¶ms, cudaStream_t stream); -------------------------------------------------------------------------------- /mamba-1p1p1/csrc/selective_scan/selective_scan_fwd_fp32.cu: -------------------------------------------------------------------------------- 1 | /****************************************************************************** 2 | * Copyright (c) 2023, Tri Dao. 3 | ******************************************************************************/ 4 | 5 | // Split into multiple files to compile in paralell 6 | 7 | #include "selective_scan_fwd_kernel.cuh" 8 | 9 | template void selective_scan_fwd_cuda(SSMParamsBase ¶ms, cudaStream_t stream); 10 | template void selective_scan_fwd_cuda(SSMParamsBase ¶ms, cudaStream_t stream); -------------------------------------------------------------------------------- /mamba-1p1p1/mamba_ssm/__init__.py: -------------------------------------------------------------------------------- 1 | __version__ = "1.1.1" 2 | 3 | from mamba_ssm.ops.selective_scan_interface import selective_scan_fn, mamba_inner_fn 4 | from mamba_ssm.modules.mamba_simple import Mamba 5 | from mamba_ssm.models.mixer_seq_simple import MambaLMHeadModel 6 | -------------------------------------------------------------------------------- /mamba-1p1p1/mamba_ssm/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/mamba-1p1p1/mamba_ssm/models/__init__.py -------------------------------------------------------------------------------- /mamba-1p1p1/mamba_ssm/models/config_mamba.py: -------------------------------------------------------------------------------- 1 | from dataclasses import dataclass, field 2 | 3 | 4 | @dataclass 5 | class MambaConfig: 6 | 7 | d_model: int = 2560 8 | d_intermediate: int = 0 9 | n_layer: int = 64 10 | vocab_size: int = 50277 11 | ssm_cfg: dict = field(default_factory=dict) 12 | attn_layer_idx: list = field(default_factory=list) 13 | attn_cfg: dict = field(default_factory=dict) 14 | rms_norm: bool = True 15 | residual_in_fp32: bool = True 16 | fused_add_norm: bool = True 17 | pad_vocab_size_multiple: int = 8 18 | tie_embeddings: bool = True 19 | -------------------------------------------------------------------------------- /mamba-1p1p1/mamba_ssm/modules/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/mamba-1p1p1/mamba_ssm/modules/__init__.py -------------------------------------------------------------------------------- /mamba-1p1p1/mamba_ssm/ops/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/mamba-1p1p1/mamba_ssm/ops/__init__.py -------------------------------------------------------------------------------- /mamba-1p1p1/mamba_ssm/ops/triton/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/mamba-1p1p1/mamba_ssm/ops/triton/__init__.py -------------------------------------------------------------------------------- /mamba-1p1p1/mamba_ssm/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hustvl/Vim/dd0358ad1e42701f22afbefa0717cc8825cf9f45/mamba-1p1p1/mamba_ssm/utils/__init__.py -------------------------------------------------------------------------------- /seg/backbone/__init__.py: -------------------------------------------------------------------------------- 1 | from .vim import VisionMambaSeg 2 | 3 | 4 | # __all__ = ['EVA2', 'VisionMambaSeg', 'DeiTSeg', 'FlashDeiTSeg'] 5 | __all__ = ['VisionMambaSeg',] -------------------------------------------------------------------------------- /seg/configs/_base_/default_runtime.py: -------------------------------------------------------------------------------- 1 | # yapf:disable 2 | log_config = dict( 3 | interval=50, 4 | hooks=[ 5 | dict(type='TextLoggerHook', by_epoch=False), 6 | # dict(type='TensorboardLoggerHook') 7 | ]) 8 | # yapf:enable 9 | dist_params = dict(backend='nccl') 10 | log_level = 'INFO' 11 | load_from = None 12 | resume_from = None 13 | workflow = [('train', 1)] 14 | cudnn_benchmark = True 15 | -------------------------------------------------------------------------------- /seg/configs/_base_/schedules/schedule_60k.py: -------------------------------------------------------------------------------- 1 | # optimizer 2 | optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005) 3 | optimizer_config = dict() 4 | # learning policy 5 | lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False) 6 | # runtime settings 7 | runner = dict(type='IterBasedRunner', max_iters=60000) 8 | checkpoint_config = dict(by_epoch=False, interval=1000, max_keep_ckpts=4) 9 | evaluation = dict(interval=1000, metric='mIoU', save_best='mIoU') 10 | -------------------------------------------------------------------------------- /seg/configs/_base_/schedules/schedule_80k.py: -------------------------------------------------------------------------------- 1 | # optimizer 2 | optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005) 3 | optimizer_config = dict() 4 | # learning policy 5 | lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False) 6 | # runtime settings 7 | runner = dict(type='IterBasedRunner', max_iters=80000) 8 | checkpoint_config = dict(by_epoch=False, interval=1000, max_keep_ckpts=10) 9 | evaluation = dict(interval=1000, metric='mIoU', save_best='mIoU') 10 | -------------------------------------------------------------------------------- /seg/mmcv_custom/__init__.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | from .checkpoint import load_checkpoint 4 | from .layer_decay_optimizer_constructor import LayerDecayOptimizerConstructor 5 | from .resize_transform import SETR_Resize 6 | from .apex_runner.optimizer import DistOptimizerHook 7 | from .train_api import train_segmentor 8 | 9 | __all__ = ['load_checkpoint', 'LayerDecayOptimizerConstructor', 'SETR_Resize', 'DistOptimizerHook', 'train_segmentor'] 10 | -------------------------------------------------------------------------------- /seg/mmcv_custom/apex_runner/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Open-MMLab. All rights reserved. 2 | from .checkpoint import save_checkpoint 3 | from .apex_iter_based_runner import IterBasedRunnerAmp 4 | 5 | 6 | __all__ = [ 7 | 'save_checkpoint', 'IterBasedRunnerAmp', 8 | ] 9 | -------------------------------------------------------------------------------- /seg/scripts/eval_vim_small_upernet.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # bash /client-tools/repair_A100.sh 3 | source /mnt/bn/lianghuidata/miniconda/bin/activate /mnt/bn/lianghuidata/miniconda/envs/vim-seg 4 | cd /mnt/bn/lianghuidata/Vim/seg 5 | 6 | SEG_CONFIG=configs/vim/upernet/upernet_vim_small_24_512_slide_60k.py 7 | TRAINED_CKPT=/mnt/bn/lianghuidata/ckpts/vim/seg/vim-s-upernet-iter-60000.pth 8 | 9 | python test.py ${SEG_CONFIG} ${TRAINED_CKPT} --eval mIoU \ 10 | --options model.backbone.if_bimamba=False model.backbone.bimamba_type=v2 optimizer.lr=1e-4 model.backbone.use_residual_as_feature=True model.backbone.last_layer_process=add optimizer.paramwise_cfg.layer_decay_rate=0.95 -------------------------------------------------------------------------------- /seg/scripts/eval_vim_tiny_upernet.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # bash /client-tools/repair_A100.sh 3 | source /mnt/bn/lianghuidata/miniconda/bin/activate /mnt/bn/lianghuidata/miniconda/envs/vim-seg 4 | cd /mnt/bn/lianghuidata/Vim/seg 5 | 6 | SEG_CONFIG=configs/vim/upernet/upernet_vim_tiny_24_512_slide_60k.py 7 | TRAINED_CKPT=/mnt/bn/lianghuidata/ckpts/vim/seg/vim-t-upernet-iter-60000.pth 8 | 9 | python test.py ${SEG_CONFIG} ${TRAINED_CKPT} --eval mIoU -------------------------------------------------------------------------------- /seg/scripts/ft_vim_small_upernet.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # bash /client-tools/repair_A100.sh 3 | source /mnt/bn/lianghuidata/miniconda/bin/activate /mnt/bn/lianghuidata/miniconda/envs/vim-seg 4 | cd /mnt/bn/lianghuidata/Vim/seg 5 | 6 | SEG_CONFIG=configs/vim/upernet/upernet_vim_small_24_512_slide_60k.py 7 | PRETRAIN_CKPT=/mnt/bn/lianghuidata/Vim/pretrained_ckpts/pretrained-vim-s.pth 8 | 9 | python3 -m torch.distributed.launch --nproc_per_node=4 --nnodes=${WORLD_SIZE} --node_rank=${RANK} --master_addr=${MASTER_ADDR} --master_port=45935 \ 10 | --use_env train.py --launcher pytorch \ 11 | ${SEG_CONFIG} \ 12 | --seed 0 --work-dir work_dirs/vimseg-s --deterministic \ 13 | --options model.backbone.pretrained=${PRETRAIN_CKPT} model.backbone.if_bimamba=False model.backbone.bimamba_type=v2 optimizer.lr=1e-4 model.backbone.use_residual_as_feature=True model.backbone.last_layer_process=add optimizer.paramwise_cfg.layer_decay_rate=0.95 -------------------------------------------------------------------------------- /seg/scripts/ft_vim_tiny_upernet.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # bash /client-tools/repair_A100.sh 3 | source /mnt/bn/lianghuidata/miniconda/bin/activate /mnt/bn/lianghuidata/miniconda/envs/vim-seg 4 | cd /mnt/bn/lianghuidata/Vim/seg 5 | 6 | SEG_CONFIG=configs/vim/upernet/upernet_vim_tiny_24_512_slide_60k.py 7 | PRETRAIN_CKPT=/mnt/bn/lianghuidata/Vim/pretrained_ckpts/pretrained-vim-t.pth 8 | 9 | python3 -m torch.distributed.launch --nproc_per_node=4 --nnodes=${WORLD_SIZE} --node_rank=${RANK} --master_addr=${MASTER_ADDR} --master_port=10295 \ 10 | --use_env train.py --launcher pytorch \ 11 | ${SEG_CONFIG} \ 12 | --seed 0 --work-dir work_dirs/vimseg-t --deterministic \ 13 | --options model.backbone.pretrained=${PRETRAIN_CKPT} model.backbone.if_bimamba=False model.backbone.bimamba_type=v2 optimizer.lr=2e-4 optimizer.weight_decay=0.1 -------------------------------------------------------------------------------- /vim/.gitignore: -------------------------------------------------------------------------------- 1 | *.swp 2 | **/__pycache__/** 3 | imnet_resnet50_scratch/timm_temp/ 4 | .dumbo.json 5 | checkpoints/ 6 | -------------------------------------------------------------------------------- /vim/hubconf.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) 2015-present, Facebook, Inc. 2 | # All rights reserved. 3 | from models import * 4 | from cait_models import * 5 | from resmlp_models import * 6 | #from patchconvnet_models import * 7 | 8 | dependencies = ["torch", "torchvision", "timm"] 9 | -------------------------------------------------------------------------------- /vim/scripts/ft-vim-s.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | conda activate 3 | cd /vim; 4 | 5 | CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m torch.distributed.launch --nproc_per_node=8 --use_env main.py --model vim_small_patch16_stride8_224_bimambav2_final_pool_mean_abs_pos_embed_with_midclstok_div2 --batch-size 128 --lr 5e-6 --min-lr 1e-5 --warmup-lr 1e-5 --drop-path 0.0 --weight-decay 1e-8 --num_workers 25 --data-path --output_dir ./output/vim_small_patch16_stride8_224_bimambav2_final_pool_mean_abs_pos_embed_with_midclstok_div2 --epochs 30 --finetune --no_amp 6 | -------------------------------------------------------------------------------- /vim/scripts/ft-vim-t.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | conda activate 3 | cd /vim; 4 | 5 | CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m torch.distributed.launch --nproc_per_node=8 --use_env main.py --model vim_tiny_patch16_stride8_224_bimambav2_final_pool_mean_abs_pos_embed_with_midclstok_div2 --batch-size 128 --lr 5e-6 --min-lr 1e-5 --warmup-lr 1e-5 --drop-path 0.0 --weight-decay 1e-8 --num_workers 25 --data-path --output_dir ./output/vim_tiny_patch16_stride8_224_bimambav2_final_pool_mean_abs_pos_embed_with_midclstok_div2 --epochs 30 --finetune --no_amp 6 | -------------------------------------------------------------------------------- /vim/scripts/pt-vim-s.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | conda activate 3 | cd /vim; 4 | 5 | CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m torch.distributed.launch --nproc_per_node=8 --use_env main.py --model vim_small_patch16_224_bimambav2_final_pool_mean_abs_pos_embed_with_midclstok_div2 --batch-size 64 --drop-path 0.05 --weight-decay 0.05 --lr 1e-3 --num_workers 25 --data-path --output_dir ./output/vim_small_patch16_224_bimambav2_final_pool_mean_abs_pos_embed_with_midclstok_div2 --no_amp 6 | -------------------------------------------------------------------------------- /vim/scripts/pt-vim-t.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | conda activate 3 | cd /vim; 4 | 5 | CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m torch.distributed.launch --nproc_per_node=8 --use_env main.py --model vim_tiny_patch16_224_bimambav2_final_pool_mean_abs_pos_embed_with_midclstok_div2 --batch-size 128 --drop-path 0.0 --weight-decay 0.1 --num_workers 25 --data-path --output_dir ./output/vim_tiny_patch16_224_bimambav2_final_pool_mean_abs_pos_embed_with_midclstok_div2 --no_amp 6 | --------------------------------------------------------------------------------