├── .dev_scripts ├── batch_test.py ├── batch_test.sh ├── benchmark_filter.py ├── convert_benchmark_script.py ├── gather_benchmark_metric.py ├── gather_models.py └── linter.sh ├── .github ├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── ISSUE_TEMPLATE │ ├── config.yml │ ├── error-report.md │ ├── feature_request.md │ ├── general_questions.md │ └── reimplementation_questions.md └── workflows │ ├── build.yml │ ├── build_pat.yml │ └── deploy.yml ├── .gitignore ├── .pre-commit-config.yaml ├── .readthedocs.yml ├── LICENSE ├── README.md ├── configs ├── _base_ │ ├── datasets │ │ ├── cityscapes_detection.py │ │ ├── cityscapes_instance.py │ │ ├── coco_detection.py │ │ ├── coco_instance.py │ │ ├── coco_instance_semantic.py │ │ ├── deepfashion.py │ │ ├── lvis_v0.5_instance.py │ │ ├── lvis_v1_instance.py │ │ ├── voc0712.py │ │ └── wider_face.py │ ├── default_runtime.py │ ├── models │ │ ├── cascade_mask_rcnn_r50_fpn.py │ │ ├── cascade_mask_rcnn_swin_fpn.py │ │ ├── cascade_rcnn_r50_fpn.py │ │ ├── fast_rcnn_r50_fpn.py │ │ ├── faster_rcnn_r50_caffe_c4.py │ │ ├── faster_rcnn_r50_caffe_dc5.py │ │ ├── faster_rcnn_r50_fpn.py │ │ ├── mask_rcnn_r50_caffe_c4.py │ │ ├── mask_rcnn_r50_fpn.py │ │ ├── mask_rcnn_swin_fpn.py │ │ ├── mask_reppointsv2_swin_bifpn.py │ │ ├── reppointsv2_swin_bifpn.py │ │ ├── retinanet_r50_fpn.py │ │ ├── rpn_r50_caffe_c4.py │ │ ├── rpn_r50_fpn.py │ │ └── ssd300.py │ └── schedules │ │ ├── schedule_1x.py │ │ ├── schedule_20e.py │ │ └── schedule_2x.py ├── albu_example │ ├── README.md │ └── mask_rcnn_r50_fpn_albu_1x_coco.py ├── atss │ ├── README.md │ ├── atss_r101_fpn_1x_coco.py │ └── atss_r50_fpn_1x_coco.py ├── carafe │ ├── README.md │ ├── faster_rcnn_r50_fpn_carafe_1x_coco.py │ └── mask_rcnn_r50_fpn_carafe_1x_coco.py ├── cascade_rcnn │ ├── README.md │ ├── cascade_mask_rcnn_r101_caffe_fpn_1x_coco.py │ ├── cascade_mask_rcnn_r101_fpn_1x_coco.py │ ├── cascade_mask_rcnn_r101_fpn_20e_coco.py │ ├── cascade_mask_rcnn_r50_caffe_fpn_1x_coco.py │ ├── cascade_mask_rcnn_r50_fpn_1x_coco.py │ ├── cascade_mask_rcnn_r50_fpn_20e_coco.py │ ├── cascade_mask_rcnn_x101_32x4d_fpn_1x_coco.py │ ├── cascade_mask_rcnn_x101_32x4d_fpn_20e_coco.py │ ├── cascade_mask_rcnn_x101_64x4d_fpn_1x_coco.py │ ├── cascade_mask_rcnn_x101_64x4d_fpn_20e_coco.py │ ├── cascade_rcnn_r101_caffe_fpn_1x_coco.py │ ├── cascade_rcnn_r101_fpn_1x_coco.py │ ├── cascade_rcnn_r101_fpn_20e_coco.py │ ├── cascade_rcnn_r50_caffe_fpn_1x_coco.py │ ├── cascade_rcnn_r50_fpn_1x_coco.py │ ├── cascade_rcnn_r50_fpn_20e_coco.py │ ├── cascade_rcnn_x101_32x4d_fpn_1x_coco.py │ ├── cascade_rcnn_x101_32x4d_fpn_20e_coco.py │ ├── cascade_rcnn_x101_64x4d_fpn_1x_coco.py │ └── cascade_rcnn_x101_64x4d_fpn_20e_coco.py ├── cascade_rpn │ ├── README.md │ ├── crpn_fast_rcnn_r50_caffe_fpn_1x_coco.py │ ├── crpn_faster_rcnn_r50_caffe_fpn_1x_coco.py │ └── crpn_r50_caffe_fpn_1x_coco.py ├── centripetalnet │ ├── README.md │ └── centripetalnet_hourglass104_mstest_16x6_210e_coco.py ├── cityscapes │ ├── README.md │ ├── faster_rcnn_r50_fpn_1x_cityscapes.py │ └── mask_rcnn_r50_fpn_1x_cityscapes.py ├── cornernet │ ├── README.md │ ├── cornernet_hourglass104_mstest_10x5_210e_coco.py │ ├── cornernet_hourglass104_mstest_32x3_210e_coco.py │ └── cornernet_hourglass104_mstest_8x6_210e_coco.py ├── dcn │ ├── README.md │ ├── cascade_mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco.py │ ├── cascade_mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco.py │ ├── cascade_mask_rcnn_x101_32x4d_fpn_dconv_c3-c5_1x_coco.py │ ├── cascade_rcnn_r101_fpn_dconv_c3-c5_1x_coco.py │ ├── cascade_rcnn_r50_fpn_dconv_c3-c5_1x_coco.py │ ├── faster_rcnn_r101_fpn_dconv_c3-c5_1x_coco.py │ ├── faster_rcnn_r50_fpn_dconv_c3-c5_1x_coco.py │ ├── faster_rcnn_r50_fpn_dpool_1x_coco.py │ ├── faster_rcnn_r50_fpn_mdconv_c3-c5_1x_coco.py │ ├── faster_rcnn_r50_fpn_mdconv_c3-c5_group4_1x_coco.py │ ├── faster_rcnn_r50_fpn_mdpool_1x_coco.py │ ├── faster_rcnn_x101_32x4d_fpn_dconv_c3-c5_1x_coco.py │ ├── mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco.py │ ├── mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco.py │ └── mask_rcnn_r50_fpn_mdconv_c3-c5_1x_coco.py ├── deepfashion │ ├── README.md │ └── mask_rcnn_r50_fpn_15e_deepfashion.py ├── detectors │ ├── README.md │ ├── cascade_rcnn_r50_rfp_1x_coco.py │ ├── cascade_rcnn_r50_sac_1x_coco.py │ ├── detectors_cascade_rcnn_r50_1x_coco.py │ ├── detectors_htc_r50_1x_coco.py │ ├── htc_r50_rfp_1x_coco.py │ └── htc_r50_sac_1x_coco.py ├── detr │ ├── README.md │ └── detr_r50_8x2_150e_coco.py ├── double_heads │ ├── README.md │ └── dh_faster_rcnn_r50_fpn_1x_coco.py ├── dynamic_rcnn │ ├── README.md │ └── dynamic_rcnn_r50_fpn_1x.py ├── empirical_attention │ ├── README.md │ ├── faster_rcnn_r50_fpn_attention_0010_1x_coco.py │ ├── faster_rcnn_r50_fpn_attention_0010_dcn_1x_coco.py │ ├── faster_rcnn_r50_fpn_attention_1111_1x_coco.py │ └── faster_rcnn_r50_fpn_attention_1111_dcn_1x_coco.py ├── fast_rcnn │ ├── README.md │ ├── fast_rcnn_r101_caffe_fpn_1x_coco.py │ ├── fast_rcnn_r101_fpn_1x_coco.py │ ├── fast_rcnn_r101_fpn_2x_coco.py │ ├── fast_rcnn_r50_caffe_fpn_1x_coco.py │ ├── fast_rcnn_r50_fpn_1x_coco.py │ └── fast_rcnn_r50_fpn_2x_coco.py ├── faster_rcnn │ ├── README.md │ ├── faster_rcnn_r101_caffe_fpn_1x_coco.py │ ├── faster_rcnn_r101_fpn_1x_coco.py │ ├── faster_rcnn_r101_fpn_2x_coco.py │ ├── faster_rcnn_r50_caffe_c4_1x_coco.py │ ├── faster_rcnn_r50_caffe_dc5_1x_coco.py │ ├── faster_rcnn_r50_caffe_dc5_mstrain_1x_coco.py │ ├── faster_rcnn_r50_caffe_dc5_mstrain_3x_coco.py │ ├── faster_rcnn_r50_caffe_fpn_1x_coco.py │ ├── faster_rcnn_r50_caffe_fpn_mstrain_1x_coco-person-bicycle-car.py │ ├── faster_rcnn_r50_caffe_fpn_mstrain_1x_coco-person.py │ ├── faster_rcnn_r50_caffe_fpn_mstrain_1x_coco.py │ ├── faster_rcnn_r50_caffe_fpn_mstrain_2x_coco.py │ ├── faster_rcnn_r50_caffe_fpn_mstrain_3x_coco.py │ ├── faster_rcnn_r50_caffe_fpn_mstrain_90k_coco.py │ ├── faster_rcnn_r50_fpn_1x_coco.py │ ├── faster_rcnn_r50_fpn_2x_coco.py │ ├── faster_rcnn_r50_fpn_bounded_iou_1x_coco.py │ ├── faster_rcnn_r50_fpn_giou_1x_coco.py │ ├── faster_rcnn_r50_fpn_iou_1x_coco.py │ ├── faster_rcnn_r50_fpn_ohem_1x_coco.py │ ├── faster_rcnn_r50_fpn_soft_nms_1x_coco.py │ ├── faster_rcnn_x101_32x4d_fpn_1x_coco.py │ ├── faster_rcnn_x101_32x4d_fpn_2x_coco.py │ ├── faster_rcnn_x101_64x4d_fpn_1x_coco.py │ └── faster_rcnn_x101_64x4d_fpn_2x_coco.py ├── fcos │ ├── README.md │ ├── fcos_center-normbbox-centeronreg-giou_r50_caffe_fpn_gn-head_1x_coco.py │ ├── fcos_center-normbbox-centeronreg-giou_r50_caffe_fpn_gn-head_dcn_1x_coco.py │ ├── fcos_center_r50_caffe_fpn_gn-head_1x_coco.py │ ├── fcos_r101_caffe_fpn_gn-head_1x_coco.py │ ├── fcos_r101_caffe_fpn_gn-head_mstrain_640-800_2x_coco.py │ ├── fcos_r50_caffe_fpn_gn-head_1x_coco.py │ ├── fcos_r50_caffe_fpn_gn-head_4x4_1x_coco.py │ ├── fcos_r50_caffe_fpn_gn-head_mstrain_640-800_2x_coco.py │ └── fcos_x101_64x4d_fpn_gn-head_mstrain_640-800_2x_coco.py ├── foveabox │ ├── README.md │ ├── fovea_align_r101_fpn_gn-head_4x4_2x_coco.py │ ├── fovea_align_r101_fpn_gn-head_mstrain_640-800_4x4_2x_coco.py │ ├── fovea_align_r50_fpn_gn-head_4x4_2x_coco.py │ ├── fovea_align_r50_fpn_gn-head_mstrain_640-800_4x4_2x_coco.py │ ├── fovea_r101_fpn_4x4_1x_coco.py │ ├── fovea_r101_fpn_4x4_2x_coco.py │ ├── fovea_r50_fpn_4x4_1x_coco.py │ └── fovea_r50_fpn_4x4_2x_coco.py ├── fp16 │ ├── README.md │ ├── faster_rcnn_r50_fpn_fp16_1x_coco.py │ ├── mask_rcnn_r50_fpn_fp16_1x_coco.py │ └── retinanet_r50_fpn_fp16_1x_coco.py ├── fpg │ ├── README.md │ ├── faster_rcnn_r50_fpg-chn128_crop640_50e_coco.py │ ├── faster_rcnn_r50_fpg_crop640_50e_coco.py │ ├── faster_rcnn_r50_fpn_crop640_50e_coco.py │ ├── mask_rcnn_r50_fpg-chn128_crop640_50e_coco.py │ ├── mask_rcnn_r50_fpg_crop640_50e_coco.py │ ├── mask_rcnn_r50_fpn_crop640_50e_coco.py │ ├── retinanet_r50_fpg-chn128_crop640_50e_coco.py │ └── retinanet_r50_fpg_crop640_50e_coco.py ├── free_anchor │ ├── README.md │ ├── retinanet_free_anchor_r101_fpn_1x_coco.py │ ├── retinanet_free_anchor_r50_fpn_1x_coco.py │ └── retinanet_free_anchor_x101_32x4d_fpn_1x_coco.py ├── fsaf │ ├── README.md │ ├── fsaf_r101_fpn_1x_coco.py │ ├── fsaf_r50_fpn_1x_coco.py │ └── fsaf_x101_64x4d_fpn_1x_coco.py ├── gcnet │ ├── README.md │ ├── cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_1x_coco.py │ ├── cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_dconv_c3-c5_1x_coco.py │ ├── cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_dconv_c3-c5_r16_gcb_c3-c5_1x_coco.py │ ├── cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_dconv_c3-c5_r4_gcb_c3-c5_1x_coco.py │ ├── cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_r16_gcb_c3-c5_1x_coco.py │ ├── cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco.py │ ├── mask_rcnn_r101_fpn_r16_gcb_c3-c5_1x_coco.py │ ├── mask_rcnn_r101_fpn_r4_gcb_c3-c5_1x_coco.py │ ├── mask_rcnn_r101_fpn_syncbn-backbone_1x_coco.py │ ├── mask_rcnn_r101_fpn_syncbn-backbone_r16_gcb_c3-c5_1x_coco.py │ ├── mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco.py │ ├── mask_rcnn_r50_fpn_r16_gcb_c3-c5_1x_coco.py │ ├── mask_rcnn_r50_fpn_r4_gcb_c3-c5_1x_coco.py │ ├── mask_rcnn_r50_fpn_syncbn-backbone_1x_coco.py │ ├── mask_rcnn_r50_fpn_syncbn-backbone_r16_gcb_c3-c5_1x_coco.py │ ├── mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco.py │ ├── mask_rcnn_x101_32x4d_fpn_syncbn-backbone_1x_coco.py │ ├── mask_rcnn_x101_32x4d_fpn_syncbn-backbone_r16_gcb_c3-c5_1x_coco.py │ └── mask_rcnn_x101_32x4d_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco.py ├── gfl │ ├── README.md │ ├── gfl_r101_fpn_dconv_c3-c5_mstrain_2x_coco.py │ ├── gfl_r101_fpn_mstrain_2x_coco.py │ ├── gfl_r50_fpn_1x_coco.py │ ├── gfl_r50_fpn_mstrain_2x_coco.py │ ├── gfl_x101_32x4d_fpn_dconv_c4-c5_mstrain_2x_coco.py │ └── gfl_x101_32x4d_fpn_mstrain_2x_coco.py ├── ghm │ ├── README.md │ ├── retinanet_ghm_r101_fpn_1x_coco.py │ ├── retinanet_ghm_r50_fpn_1x_coco.py │ ├── retinanet_ghm_x101_32x4d_fpn_1x_coco.py │ └── retinanet_ghm_x101_64x4d_fpn_1x_coco.py ├── gn+ws │ ├── README.md │ ├── faster_rcnn_r101_fpn_gn_ws-all_1x_coco.py │ ├── faster_rcnn_r50_fpn_gn_ws-all_1x_coco.py │ ├── faster_rcnn_x101_32x4d_fpn_gn_ws-all_1x_coco.py │ ├── faster_rcnn_x50_32x4d_fpn_gn_ws-all_1x_coco.py │ ├── mask_rcnn_r101_fpn_gn_ws-all_20_23_24e_coco.py │ ├── mask_rcnn_r101_fpn_gn_ws-all_2x_coco.py │ ├── mask_rcnn_r50_fpn_gn_ws-all_20_23_24e_coco.py │ ├── mask_rcnn_r50_fpn_gn_ws-all_2x_coco.py │ ├── mask_rcnn_x101_32x4d_fpn_gn_ws-all_20_23_24e_coco.py │ ├── mask_rcnn_x101_32x4d_fpn_gn_ws-all_2x_coco.py │ ├── mask_rcnn_x50_32x4d_fpn_gn_ws-all_20_23_24e_coco.py │ └── mask_rcnn_x50_32x4d_fpn_gn_ws-all_2x_coco.py ├── gn │ ├── README.md │ ├── mask_rcnn_r101_fpn_gn-all_2x_coco.py │ ├── mask_rcnn_r101_fpn_gn-all_3x_coco.py │ ├── mask_rcnn_r50_fpn_gn-all_2x_coco.py │ ├── mask_rcnn_r50_fpn_gn-all_3x_coco.py │ ├── mask_rcnn_r50_fpn_gn-all_contrib_2x_coco.py │ └── mask_rcnn_r50_fpn_gn-all_contrib_3x_coco.py ├── grid_rcnn │ ├── README.md │ ├── grid_rcnn_r101_fpn_gn-head_2x_coco.py │ ├── grid_rcnn_r50_fpn_gn-head_1x_coco.py │ ├── grid_rcnn_r50_fpn_gn-head_2x_coco.py │ ├── grid_rcnn_x101_32x4d_fpn_gn-head_2x_coco.py │ └── grid_rcnn_x101_64x4d_fpn_gn-head_2x_coco.py ├── groie │ ├── README.md │ ├── faster_rcnn_r50_fpn_groie_1x_coco.py │ ├── grid_rcnn_r50_fpn_gn-head_groie_1x_coco.py │ ├── mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco.py │ ├── mask_rcnn_r50_fpn_groie_1x_coco.py │ └── mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco.py ├── guided_anchoring │ ├── README.md │ ├── ga_fast_r50_caffe_fpn_1x_coco.py │ ├── ga_faster_r101_caffe_fpn_1x_coco.py │ ├── ga_faster_r50_caffe_fpn_1x_coco.py │ ├── ga_faster_r50_fpn_1x_coco.py │ ├── ga_faster_x101_32x4d_fpn_1x_coco.py │ ├── ga_faster_x101_64x4d_fpn_1x_coco.py │ ├── ga_retinanet_r101_caffe_fpn_1x_coco.py │ ├── ga_retinanet_r101_caffe_fpn_mstrain_2x.py │ ├── ga_retinanet_r50_caffe_fpn_1x_coco.py │ ├── ga_retinanet_r50_fpn_1x_coco.py │ ├── ga_retinanet_x101_32x4d_fpn_1x_coco.py │ ├── ga_retinanet_x101_64x4d_fpn_1x_coco.py │ ├── ga_rpn_r101_caffe_fpn_1x_coco.py │ ├── ga_rpn_r50_caffe_fpn_1x_coco.py │ ├── ga_rpn_r50_fpn_1x_coco.py │ ├── ga_rpn_x101_32x4d_fpn_1x_coco.py │ └── ga_rpn_x101_64x4d_fpn_1x_coco.py ├── hrnet │ ├── README.md │ ├── cascade_mask_rcnn_hrnetv2p_w18_20e_coco.py │ ├── cascade_mask_rcnn_hrnetv2p_w32_20e_coco.py │ ├── cascade_mask_rcnn_hrnetv2p_w40_20e_coco.py │ ├── cascade_rcnn_hrnetv2p_w18_20e_coco.py │ ├── cascade_rcnn_hrnetv2p_w32_20e_coco.py │ ├── cascade_rcnn_hrnetv2p_w40_20e_coco.py │ ├── faster_rcnn_hrnetv2p_w18_1x_coco.py │ ├── faster_rcnn_hrnetv2p_w18_2x_coco.py │ ├── faster_rcnn_hrnetv2p_w32_1x_coco.py │ ├── faster_rcnn_hrnetv2p_w32_2x_coco.py │ ├── faster_rcnn_hrnetv2p_w40_1x_coco.py │ ├── faster_rcnn_hrnetv2p_w40_2x_coco.py │ ├── fcos_hrnetv2p_w18_gn-head_4x4_1x_coco.py │ ├── fcos_hrnetv2p_w18_gn-head_4x4_2x_coco.py │ ├── fcos_hrnetv2p_w18_gn-head_mstrain_640-800_4x4_2x_coco.py │ ├── fcos_hrnetv2p_w32_gn-head_4x4_1x_coco.py │ ├── fcos_hrnetv2p_w32_gn-head_4x4_2x_coco.py │ ├── fcos_hrnetv2p_w32_gn-head_mstrain_640-800_4x4_2x_coco.py │ ├── fcos_hrnetv2p_w40_gn-head_mstrain_640-800_4x4_2x_coco.py │ ├── htc_hrnetv2p_w18_20e_coco.py │ ├── htc_hrnetv2p_w32_20e_coco.py │ ├── htc_hrnetv2p_w40_20e_coco.py │ ├── htc_hrnetv2p_w40_28e_coco.py │ ├── htc_x101_64x4d_fpn_16x1_28e_coco.py │ ├── mask_rcnn_hrnetv2p_w18_1x_coco.py │ ├── mask_rcnn_hrnetv2p_w18_2x_coco.py │ ├── mask_rcnn_hrnetv2p_w32_1x_coco.py │ ├── mask_rcnn_hrnetv2p_w32_2x_coco.py │ ├── mask_rcnn_hrnetv2p_w40_1x_coco.py │ └── mask_rcnn_hrnetv2p_w40_2x_coco.py ├── htc │ ├── README.md │ ├── htc_r101_fpn_20e_coco.py │ ├── htc_r50_fpn_1x_coco.py │ ├── htc_r50_fpn_20e_coco.py │ ├── htc_without_semantic_r50_fpn_1x_coco.py │ ├── htc_x101_32x4d_fpn_16x1_20e_coco.py │ ├── htc_x101_64x4d_fpn_16x1_20e_coco.py │ └── htc_x101_64x4d_fpn_dconv_c3-c5_mstrain_400_1400_16x1_20e_coco.py ├── instaboost │ ├── README.md │ ├── cascade_mask_rcnn_r101_fpn_instaboost_4x_coco.py │ ├── cascade_mask_rcnn_r50_fpn_instaboost_4x_coco.py │ ├── cascade_mask_rcnn_x101_64x4d_fpn_instaboost_4x_coco.py │ ├── mask_rcnn_r101_fpn_instaboost_4x_coco.py │ ├── mask_rcnn_r50_fpn_instaboost_4x_coco.py │ └── mask_rcnn_x101_64x4d_fpn_instaboost_4x_coco.py ├── ld │ ├── ld_r101_gflv1_r101dcn_fpn_coco_2x.py │ ├── ld_r18_gflv1_r101_fpn_coco_1x.py │ ├── ld_r34_gflv1_r101_fpn_coco_1x.py │ ├── ld_r50_gflv1_r101_fpn_coco_1x.py │ └── readme.md ├── legacy_1.x │ ├── README.md │ ├── cascade_mask_rcnn_r50_fpn_1x_coco_v1.py │ ├── faster_rcnn_r50_fpn_1x_coco_v1.py │ ├── mask_rcnn_r50_fpn_1x_coco_v1.py │ ├── retinanet_r50_caffe_fpn_1x_coco_v1.py │ ├── retinanet_r50_fpn_1x_coco_v1.py │ └── ssd300_coco_v1.py ├── libra_rcnn │ ├── README.md │ ├── libra_fast_rcnn_r50_fpn_1x_coco.py │ ├── libra_faster_rcnn_r101_fpn_1x_coco.py │ ├── libra_faster_rcnn_r50_fpn_1x_coco.py │ ├── libra_faster_rcnn_x101_64x4d_fpn_1x_coco.py │ └── libra_retinanet_r50_fpn_1x_coco.py ├── lvis │ ├── README.md │ ├── mask_rcnn_r101_fpn_sample1e-3_mstrain_1x_lvis_v1.py │ ├── mask_rcnn_r101_fpn_sample1e-3_mstrain_2x_lvis_v0.5.py │ ├── mask_rcnn_r50_fpn_sample1e-3_mstrain_1x_lvis_v1.py │ ├── mask_rcnn_r50_fpn_sample1e-3_mstrain_2x_lvis_v0.5.py │ ├── mask_rcnn_x101_32x4d_fpn_sample1e-3_mstrain_1x_lvis_v1.py │ ├── mask_rcnn_x101_32x4d_fpn_sample1e-3_mstrain_2x_lvis_v0.5.py │ ├── mask_rcnn_x101_64x4d_fpn_sample1e-3_mstrain_1x_lvis_v1.py │ └── mask_rcnn_x101_64x4d_fpn_sample1e-3_mstrain_2x_lvis_v0.5.py ├── mask_rcnn │ ├── README.md │ ├── mask_rcnn_r101_caffe_fpn_1x_coco.py │ ├── mask_rcnn_r101_fpn_1x_coco.py │ ├── mask_rcnn_r101_fpn_2x_coco.py │ ├── mask_rcnn_r50_caffe_c4_1x_coco.py │ ├── mask_rcnn_r50_caffe_fpn_1x_coco.py │ ├── mask_rcnn_r50_caffe_fpn_mstrain-poly_1x_coco.py │ ├── mask_rcnn_r50_caffe_fpn_mstrain-poly_2x_coco.py │ ├── mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco.py │ ├── mask_rcnn_r50_caffe_fpn_mstrain_1x_coco.py │ ├── mask_rcnn_r50_caffe_fpn_poly_1x_coco_v1.py │ ├── mask_rcnn_r50_fpn_1x_coco.py │ ├── mask_rcnn_r50_fpn_2x_coco.py │ ├── mask_rcnn_r50_fpn_poly_1x_coco.py │ ├── mask_rcnn_x101_32x4d_fpn_1x_coco.py │ ├── mask_rcnn_x101_32x4d_fpn_2x_coco.py │ ├── mask_rcnn_x101_32x8d_fpn_1x_coco.py │ ├── mask_rcnn_x101_32x8d_fpn_mstrain-poly_1x_coco.py │ ├── mask_rcnn_x101_32x8d_fpn_mstrain-poly_3x_coco.py │ ├── mask_rcnn_x101_64x4d_fpn_1x_coco.py │ └── mask_rcnn_x101_64x4d_fpn_2x_coco.py ├── ms_rcnn │ ├── README.md │ ├── ms_rcnn_r101_caffe_fpn_1x_coco.py │ ├── ms_rcnn_r101_caffe_fpn_2x_coco.py │ ├── ms_rcnn_r50_caffe_fpn_1x_coco.py │ ├── ms_rcnn_r50_caffe_fpn_2x_coco.py │ ├── ms_rcnn_r50_fpn_1x_coco.py │ ├── ms_rcnn_x101_32x4d_fpn_1x_coco.py │ ├── ms_rcnn_x101_64x4d_fpn_1x_coco.py │ └── ms_rcnn_x101_64x4d_fpn_2x_coco.py ├── nas_fcos │ ├── README.md │ ├── nas_fcos_fcoshead_r50_caffe_fpn_gn-head_4x4_1x_coco.py │ └── nas_fcos_nashead_r50_caffe_fpn_gn-head_4x4_1x_coco.py ├── nas_fpn │ ├── README.md │ ├── retinanet_r50_fpn_crop640_50e_coco.py │ └── retinanet_r50_nasfpn_crop640_50e_coco.py ├── paa │ ├── README.md │ ├── paa_r101_fpn_1x_coco.py │ ├── paa_r101_fpn_2x_coco.py │ ├── paa_r101_fpn_mstrain_3x_coco.py │ ├── paa_r50_fpn_1.5x_coco.py │ ├── paa_r50_fpn_1x_coco.py │ ├── paa_r50_fpn_2x_coco.py │ └── paa_r50_fpn_mstrain_3x_coco.py ├── pafpn │ ├── README.md │ └── faster_rcnn_r50_pafpn_1x_coco.py ├── pascal_voc │ ├── README.md │ ├── faster_rcnn_r50_fpn_1x_voc0712.py │ ├── faster_rcnn_r50_fpn_1x_voc0712_cocofmt.py │ ├── retinanet_r50_fpn_1x_voc0712.py │ ├── ssd300_voc0712.py │ └── ssd512_voc0712.py ├── pisa │ ├── README.md │ ├── pisa_faster_rcnn_r50_fpn_1x_coco.py │ ├── pisa_faster_rcnn_x101_32x4d_fpn_1x_coco.py │ ├── pisa_mask_rcnn_r50_fpn_1x_coco.py │ ├── pisa_mask_rcnn_x101_32x4d_fpn_1x_coco.py │ ├── pisa_retinanet_r50_fpn_1x_coco.py │ ├── pisa_retinanet_x101_32x4d_fpn_1x_coco.py │ ├── pisa_ssd300_coco.py │ └── pisa_ssd512_coco.py ├── point_rend │ ├── README.md │ ├── point_rend_r50_caffe_fpn_mstrain_1x_coco.py │ └── point_rend_r50_caffe_fpn_mstrain_3x_coco.py ├── regnet │ ├── README.md │ ├── faster_rcnn_regnetx-3.2GF_fpn_1x_coco.py │ ├── faster_rcnn_regnetx-3.2GF_fpn_2x_coco.py │ ├── faster_rcnn_regnetx-3.2GF_fpn_mstrain_3x_coco.py │ ├── mask_rcnn_regnetx-12GF_fpn_1x_coco.py │ ├── mask_rcnn_regnetx-3.2GF_fpn_1x_coco.py │ ├── mask_rcnn_regnetx-3.2GF_fpn_mdconv_c3-c5_1x_coco.py │ ├── mask_rcnn_regnetx-3.2GF_fpn_mstrain_3x_coco.py │ ├── mask_rcnn_regnetx-4GF_fpn_1x_coco.py │ ├── mask_rcnn_regnetx-6.4GF_fpn_1x_coco.py │ ├── mask_rcnn_regnetx-8GF_fpn_1x_coco.py │ ├── retinanet_regnetx-1.6GF_fpn_1x_coco.py │ ├── retinanet_regnetx-3.2GF_fpn_1x_coco.py │ └── retinanet_regnetx-800MF_fpn_1x_coco.py ├── reppoints │ ├── README.md │ ├── bbox_r50_grid_center_fpn_gn-neck+head_1x_coco.py │ ├── bbox_r50_grid_fpn_gn-neck+head_1x_coco.py │ ├── reppoints.png │ ├── reppoints_minmax_r50_fpn_gn-neck+head_1x_coco.py │ ├── reppoints_moment_r101_fpn_dconv_c3-c5_gn-neck+head_2x_coco.py │ ├── reppoints_moment_r101_fpn_gn-neck+head_2x_coco.py │ ├── reppoints_moment_r50_fpn_1x_coco.py │ ├── reppoints_moment_r50_fpn_gn-neck+head_1x_coco.py │ ├── reppoints_moment_r50_fpn_gn-neck+head_2x_coco.py │ ├── reppoints_moment_x101_fpn_dconv_c3-c5_gn-neck+head_2x_coco.py │ └── reppoints_partial_minmax_r50_fpn_gn-neck+head_1x_coco.py ├── res2net │ ├── README.md │ ├── cascade_mask_rcnn_r2_101_fpn_20e_coco.py │ ├── cascade_rcnn_r2_101_fpn_20e_coco.py │ ├── faster_rcnn_r2_101_fpn_2x_coco.py │ ├── htc_r2_101_fpn_20e_coco.py │ └── mask_rcnn_r2_101_fpn_2x_coco.py ├── resnest │ ├── README.md │ ├── cascade_mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco.py │ ├── cascade_mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco.py │ ├── cascade_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py │ ├── cascade_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py │ ├── faster_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py │ ├── faster_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py │ ├── mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco.py │ └── mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco.py ├── retinanet │ ├── README.md │ ├── retinanet_r101_caffe_fpn_1x_coco.py │ ├── retinanet_r101_fpn_1x_coco.py │ ├── retinanet_r101_fpn_2x_coco.py │ ├── retinanet_r50_caffe_fpn_1x_coco.py │ ├── retinanet_r50_caffe_fpn_mstrain_1x_coco.py │ ├── retinanet_r50_caffe_fpn_mstrain_2x_coco.py │ ├── retinanet_r50_caffe_fpn_mstrain_3x_coco.py │ ├── retinanet_r50_fpn_1x_coco.py │ ├── retinanet_r50_fpn_2x_coco.py │ ├── retinanet_x101_32x4d_fpn_1x_coco.py │ ├── retinanet_x101_32x4d_fpn_2x_coco.py │ ├── retinanet_x101_64x4d_fpn_1x_coco.py │ └── retinanet_x101_64x4d_fpn_2x_coco.py ├── rpn │ ├── README.md │ ├── rpn_r101_caffe_fpn_1x_coco.py │ ├── rpn_r101_fpn_1x_coco.py │ ├── rpn_r101_fpn_2x_coco.py │ ├── rpn_r50_caffe_c4_1x_coco.py │ ├── rpn_r50_caffe_fpn_1x_coco.py │ ├── rpn_r50_fpn_1x_coco.py │ ├── rpn_r50_fpn_2x_coco.py │ ├── rpn_x101_32x4d_fpn_1x_coco.py │ ├── rpn_x101_32x4d_fpn_2x_coco.py │ ├── rpn_x101_64x4d_fpn_1x_coco.py │ └── rpn_x101_64x4d_fpn_2x_coco.py ├── sabl │ ├── README.md │ ├── sabl_cascade_rcnn_r101_fpn_1x_coco.py │ ├── sabl_cascade_rcnn_r50_fpn_1x_coco.py │ ├── sabl_faster_rcnn_r101_fpn_1x_coco.py │ ├── sabl_faster_rcnn_r50_fpn_1x_coco.py │ ├── sabl_retinanet_r101_fpn_1x_coco.py │ ├── sabl_retinanet_r101_fpn_gn_1x_coco.py │ ├── sabl_retinanet_r101_fpn_gn_2x_ms_480_960_coco.py │ ├── sabl_retinanet_r101_fpn_gn_2x_ms_640_800_coco.py │ ├── sabl_retinanet_r50_fpn_1x_coco.py │ └── sabl_retinanet_r50_fpn_gn_1x_coco.py ├── scnet │ ├── README.md │ ├── scnet_r101_fpn_20e_coco.py │ ├── scnet_r50_fpn_1x_coco.py │ ├── scnet_r50_fpn_20e_coco.py │ ├── scnet_x101_64x4d_fpn_20e_coco.py │ └── scnet_x101_64x4d_fpn_8x1_20e_coco.py ├── scratch │ ├── README.md │ ├── faster_rcnn_r50_fpn_gn-all_scratch_6x_coco.py │ └── mask_rcnn_r50_fpn_gn-all_scratch_6x_coco.py ├── sparse_rcnn │ ├── README.md │ ├── sparse_rcnn_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco.py │ ├── sparse_rcnn_r101_fpn_mstrain_480-800_3x_coco.py │ ├── sparse_rcnn_r50_fpn_1x_coco.py │ ├── sparse_rcnn_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco.py │ └── sparse_rcnn_r50_fpn_mstrain_480-800_3x_coco.py ├── ssd │ ├── README.md │ ├── ssd300_coco.py │ └── ssd512_coco.py ├── swin │ ├── cascade_mask_rcnn_swin_base_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco.py │ ├── cascade_mask_rcnn_swin_small_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco.py │ ├── cascade_mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_1x_coco.py │ ├── cascade_mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco.py │ ├── mask_rcnn_swin_small_patch4_window7_mstrain_480-800_adamw_3x_coco.py │ ├── mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_1x_coco.py │ ├── mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_3x_coco.py │ ├── mask_reppoitsv2_swin_tiny_patch4_window7_mstrain_480_960_giou_gfocal_bifpn_adamw_3x_coco.py │ └── reppoitsv2_swin_tiny_patch4_window7_mstrain_480_960_giou_gfocal_bifpn_adamw_3x_coco.py ├── tridentnet │ ├── README.md │ ├── tridentnet_r50_caffe_1x_coco.py │ ├── tridentnet_r50_caffe_mstrain_1x_coco.py │ └── tridentnet_r50_caffe_mstrain_3x_coco.py ├── vfnet │ ├── README.md │ ├── vfnet_r101_fpn_1x_coco.py │ ├── vfnet_r101_fpn_2x_coco.py │ ├── vfnet_r101_fpn_mdconv_c3-c5_mstrain_2x_coco.py │ ├── vfnet_r101_fpn_mstrain_2x_coco.py │ ├── vfnet_r2_101_fpn_mdconv_c3-c5_mstrain_2x_coco.py │ ├── vfnet_r2_101_fpn_mstrain_2x_coco.py │ ├── vfnet_r50_fpn_1x_coco.py │ ├── vfnet_r50_fpn_mdconv_c3-c5_mstrain_2x_coco.py │ ├── vfnet_r50_fpn_mstrain_2x_coco.py │ ├── vfnet_x101_32x4d_fpn_mdconv_c3-c5_mstrain_2x_coco.py │ ├── vfnet_x101_32x4d_fpn_mstrain_2x_coco.py │ ├── vfnet_x101_64x4d_fpn_mdconv_c3-c5_mstrain_2x_coco.py │ └── vfnet_x101_64x4d_fpn_mstrain_2x_coco.py ├── wider_face │ ├── README.md │ └── ssd300_wider_face.py ├── yolact │ ├── README.md │ ├── yolact_r101_1x8_coco.py │ ├── yolact_r50_1x8_coco.py │ └── yolact_r50_8x8_coco.py └── yolo │ ├── README.md │ ├── yolov3_d53_320_273e_coco.py │ ├── yolov3_d53_mstrain-416_273e_coco.py │ └── yolov3_d53_mstrain-608_273e_coco.py ├── demo ├── MMDet_Tutorial.ipynb ├── create_result_gif.py ├── demo.jpg ├── demo.mp4 ├── image_demo.py ├── inference_demo.ipynb ├── video_demo.py └── webcam_demo.py ├── docker ├── Dockerfile └── serve │ ├── Dockerfile │ ├── config.properties │ └── entrypoint.sh ├── docs ├── 1_exist_data_model.md ├── 2_new_data_model.md ├── 3_exist_data_new_model.md ├── Makefile ├── api.rst ├── changelog.md ├── compatibility.md ├── conf.py ├── conventions.md ├── faq.md ├── get_started.md ├── index.rst ├── make.bat ├── model_zoo.md ├── projects.md ├── robustness_benchmarking.md ├── stat.py ├── tutorials │ ├── config.md │ ├── customize_dataset.md │ ├── customize_losses.md │ ├── customize_models.md │ ├── customize_runtime.md │ ├── data_pipeline.md │ ├── finetune.md │ ├── index.rst │ ├── onnx2tensorrt.md │ └── pytorch2onnx.md └── useful_tools.md ├── mmcv_custom ├── __init__.py ├── checkpoint.py └── runner │ ├── __init__.py │ ├── checkpoint.py │ └── epoch_based_runner.py ├── mmdet ├── __init__.py ├── apis │ ├── __init__.py │ ├── inference.py │ ├── test.py │ └── train.py ├── core │ ├── __init__.py │ ├── anchor │ │ ├── __init__.py │ │ ├── anchor_generator.py │ │ ├── builder.py │ │ ├── point_generator.py │ │ └── utils.py │ ├── bbox │ │ ├── __init__.py │ │ ├── assigners │ │ │ ├── __init__.py │ │ │ ├── approx_max_iou_assigner.py │ │ │ ├── assign_result.py │ │ │ ├── atss_assigner.py │ │ │ ├── atss_assigner_v2.py │ │ │ ├── base_assigner.py │ │ │ ├── center_region_assigner.py │ │ │ ├── grid_assigner.py │ │ │ ├── hungarian_assigner.py │ │ │ ├── max_iou_assigner.py │ │ │ ├── point_assigner.py │ │ │ ├── point_assigner_v2.py │ │ │ ├── point_hm_assigner.py │ │ │ └── region_assigner.py │ │ ├── builder.py │ │ ├── coder │ │ │ ├── __init__.py │ │ │ ├── base_bbox_coder.py │ │ │ ├── bucketing_bbox_coder.py │ │ │ ├── delta_xywh_bbox_coder.py │ │ │ ├── legacy_delta_xywh_bbox_coder.py │ │ │ ├── pseudo_bbox_coder.py │ │ │ ├── tblr_bbox_coder.py │ │ │ └── yolo_bbox_coder.py │ │ ├── demodata.py │ │ ├── iou_calculators │ │ │ ├── __init__.py │ │ │ ├── builder.py │ │ │ └── iou2d_calculator.py │ │ ├── match_costs │ │ │ ├── __init__.py │ │ │ ├── builder.py │ │ │ └── match_cost.py │ │ ├── samplers │ │ │ ├── __init__.py │ │ │ ├── base_sampler.py │ │ │ ├── combined_sampler.py │ │ │ ├── instance_balanced_pos_sampler.py │ │ │ ├── iou_balanced_neg_sampler.py │ │ │ ├── ohem_sampler.py │ │ │ ├── pseudo_sampler.py │ │ │ ├── random_sampler.py │ │ │ ├── sampling_result.py │ │ │ └── score_hlr_sampler.py │ │ └── transforms.py │ ├── evaluation │ │ ├── __init__.py │ │ ├── bbox_overlaps.py │ │ ├── class_names.py │ │ ├── eval_hooks.py │ │ ├── mean_ap.py │ │ └── recall.py │ ├── export │ │ ├── __init__.py │ │ └── pytorch2onnx.py │ ├── mask │ │ ├── __init__.py │ │ ├── mask_target.py │ │ ├── structures.py │ │ └── utils.py │ ├── post_processing │ │ ├── __init__.py │ │ ├── bbox_nms.py │ │ └── merge_augs.py │ ├── utils │ │ ├── __init__.py │ │ ├── dist_utils.py │ │ └── misc.py │ └── visualization │ │ ├── __init__.py │ │ └── image.py ├── datasets │ ├── __init__.py │ ├── builder.py │ ├── cityscapes.py │ ├── coco.py │ ├── custom.py │ ├── dataset_wrappers.py │ ├── deepfashion.py │ ├── lvis.py │ ├── pipelines │ │ ├── __init__.py │ │ ├── auto_augment.py │ │ ├── compose.py │ │ ├── formating.py │ │ ├── instaboost.py │ │ ├── loading.py │ │ ├── test_time_aug.py │ │ └── transforms.py │ ├── samplers │ │ ├── __init__.py │ │ ├── distributed_sampler.py │ │ └── group_sampler.py │ ├── utils.py │ ├── voc.py │ ├── wider_face.py │ └── xml_style.py ├── models │ ├── __init__.py │ ├── backbones │ │ ├── __init__.py │ │ ├── darknet.py │ │ ├── detectors_resnet.py │ │ ├── detectors_resnext.py │ │ ├── hourglass.py │ │ ├── hrnet.py │ │ ├── regnet.py │ │ ├── res2net.py │ │ ├── resnest.py │ │ ├── resnet.py │ │ ├── resnext.py │ │ ├── ssd_vgg.py │ │ ├── swin_transformer.py │ │ └── trident_resnet.py │ ├── builder.py │ ├── dense_heads │ │ ├── __init__.py │ │ ├── anchor_free_head.py │ │ ├── anchor_head.py │ │ ├── atss_head.py │ │ ├── base_dense_head.py │ │ ├── cascade_rpn_head.py │ │ ├── centripetal_head.py │ │ ├── corner_head.py │ │ ├── dense_test_mixins.py │ │ ├── embedding_rpn_head.py │ │ ├── fcos_head.py │ │ ├── fovea_head.py │ │ ├── free_anchor_retina_head.py │ │ ├── fsaf_head.py │ │ ├── ga_retina_head.py │ │ ├── ga_rpn_head.py │ │ ├── gfl_head.py │ │ ├── guided_anchor_head.py │ │ ├── ld_head.py │ │ ├── nasfcos_head.py │ │ ├── paa_head.py │ │ ├── pisa_retinanet_head.py │ │ ├── pisa_ssd_head.py │ │ ├── reppoints_head.py │ │ ├── reppoints_v2_head.py │ │ ├── retina_head.py │ │ ├── retina_sepbn_head.py │ │ ├── rpn_head.py │ │ ├── rpn_test_mixin.py │ │ ├── sabl_retina_head.py │ │ ├── ssd_head.py │ │ ├── transformer_head.py │ │ ├── vfnet_head.py │ │ ├── yolact_head.py │ │ └── yolo_head.py │ ├── detectors │ │ ├── __init__.py │ │ ├── atss.py │ │ ├── base.py │ │ ├── cascade_rcnn.py │ │ ├── cornernet.py │ │ ├── detr.py │ │ ├── fast_rcnn.py │ │ ├── faster_rcnn.py │ │ ├── fcos.py │ │ ├── fovea.py │ │ ├── fsaf.py │ │ ├── gfl.py │ │ ├── grid_rcnn.py │ │ ├── htc.py │ │ ├── kd_one_stage.py │ │ ├── mask_rcnn.py │ │ ├── mask_reppoints_v2_detector.py │ │ ├── mask_scoring_rcnn.py │ │ ├── nasfcos.py │ │ ├── paa.py │ │ ├── point_rend.py │ │ ├── reppoints_detector.py │ │ ├── reppoints_v2_detector.py │ │ ├── retinanet.py │ │ ├── rpn.py │ │ ├── scnet.py │ │ ├── single_stage.py │ │ ├── sparse_rcnn.py │ │ ├── trident_faster_rcnn.py │ │ ├── two_stage.py │ │ ├── vfnet.py │ │ ├── yolact.py │ │ └── yolo.py │ ├── losses │ │ ├── __init__.py │ │ ├── accuracy.py │ │ ├── ae_loss.py │ │ ├── balanced_l1_loss.py │ │ ├── cross_entropy_loss.py │ │ ├── focal_loss.py │ │ ├── gaussian_focal_loss.py │ │ ├── gfocal_loss.py │ │ ├── ghm_loss.py │ │ ├── iou_loss.py │ │ ├── kd_loss.py │ │ ├── mse_loss.py │ │ ├── pisa_loss.py │ │ ├── smooth_l1_loss.py │ │ ├── utils.py │ │ └── varifocal_loss.py │ ├── necks │ │ ├── __init__.py │ │ ├── bfp.py │ │ ├── bifpn.py │ │ ├── channel_mapper.py │ │ ├── fpg.py │ │ ├── fpn.py │ │ ├── fpn_carafe.py │ │ ├── hrfpn.py │ │ ├── nas_fpn.py │ │ ├── nasfcos_fpn.py │ │ ├── pafpn.py │ │ ├── rfp.py │ │ └── yolo_neck.py │ ├── roi_heads │ │ ├── __init__.py │ │ ├── base_roi_head.py │ │ ├── bbox_heads │ │ │ ├── __init__.py │ │ │ ├── bbox_head.py │ │ │ ├── convfc_bbox_head.py │ │ │ ├── dii_head.py │ │ │ ├── double_bbox_head.py │ │ │ ├── sabl_head.py │ │ │ └── scnet_bbox_head.py │ │ ├── cascade_roi_head.py │ │ ├── double_roi_head.py │ │ ├── dynamic_roi_head.py │ │ ├── grid_roi_head.py │ │ ├── htc_roi_head.py │ │ ├── mask_heads │ │ │ ├── __init__.py │ │ │ ├── coarse_mask_head.py │ │ │ ├── condconv_mask_head.py │ │ │ ├── fcn_mask_head.py │ │ │ ├── feature_relay_head.py │ │ │ ├── fused_semantic_head.py │ │ │ ├── global_context_head.py │ │ │ ├── grid_head.py │ │ │ ├── htc_mask_head.py │ │ │ ├── mask_point_head.py │ │ │ ├── maskiou_head.py │ │ │ ├── scnet_mask_head.py │ │ │ └── scnet_semantic_head.py │ │ ├── mask_scoring_roi_head.py │ │ ├── pisa_roi_head.py │ │ ├── point_rend_roi_head.py │ │ ├── roi_extractors │ │ │ ├── __init__.py │ │ │ ├── base_roi_extractor.py │ │ │ ├── generic_roi_extractor.py │ │ │ └── single_level_roi_extractor.py │ │ ├── scnet_roi_head.py │ │ ├── shared_heads │ │ │ ├── __init__.py │ │ │ └── res_layer.py │ │ ├── sparse_roi_head.py │ │ ├── standard_roi_head.py │ │ ├── test_mixins.py │ │ └── trident_roi_head.py │ └── utils │ │ ├── __init__.py │ │ ├── builder.py │ │ ├── gaussian_target.py │ │ ├── positional_encoding.py │ │ ├── res_layer.py │ │ └── transformer.py ├── utils │ ├── __init__.py │ ├── collect_env.py │ ├── common.py │ ├── contextmanagers.py │ ├── instances.py │ ├── logger.py │ ├── optimizer.py │ ├── profiling.py │ ├── util_mixins.py │ └── util_random.py └── version.py ├── pytest.ini ├── requirements.txt ├── requirements ├── build.txt ├── docs.txt ├── optional.txt ├── readthedocs.txt ├── runtime.txt └── tests.txt ├── resources ├── coco_test_12510.jpg ├── corruptions_sev_3.png ├── data_pipeline.png ├── loss_curve.png └── mmdet-logo.png ├── setup.cfg ├── setup.py ├── tests ├── data │ ├── VOCdevkit │ │ ├── VOC2007 │ │ │ ├── Annotations │ │ │ │ └── 000001.xml │ │ │ ├── ImageSets │ │ │ │ └── Main │ │ │ │ │ ├── test.txt │ │ │ │ │ └── trainval.txt │ │ │ └── JPEGImages │ │ │ │ └── 000001.jpg │ │ └── VOC2012 │ │ │ ├── Annotations │ │ │ └── 000001.xml │ │ │ ├── ImageSets │ │ │ └── Main │ │ │ │ ├── test.txt │ │ │ │ └── trainval.txt │ │ │ └── JPEGImages │ │ │ └── 000001.jpg │ ├── coco_sample.json │ ├── color.jpg │ └── gray.jpg ├── test_data │ ├── test_datasets │ │ ├── test_coco_dataset.py │ │ ├── test_common.py │ │ ├── test_custom_dataset.py │ │ ├── test_dataset_wrapper.py │ │ └── test_xml_dataset.py │ ├── test_pipelines │ │ ├── test_formatting.py │ │ ├── test_loading.py │ │ ├── test_sampler.py │ │ └── test_transform │ │ │ ├── test_img_augment.py │ │ │ ├── test_models_aug_test.py │ │ │ ├── test_rotate.py │ │ │ ├── test_shear.py │ │ │ ├── test_transform.py │ │ │ └── test_translate.py │ └── test_utils.py ├── test_metrics │ ├── test_box_overlap.py │ └── test_losses.py ├── test_models │ ├── test_backbones │ │ ├── __init__.py │ │ ├── test_hourglass.py │ │ ├── test_regnet.py │ │ ├── test_renext.py │ │ ├── test_res2net.py │ │ ├── test_resnest.py │ │ ├── test_resnet.py │ │ ├── test_trident_resnet.py │ │ └── utils.py │ ├── test_dense_heads │ │ ├── test_anchor_head.py │ │ ├── test_corner_head.py │ │ ├── test_fcos_head.py │ │ ├── test_fsaf_head.py │ │ ├── test_ga_anchor_head.py │ │ ├── test_ld_head.py │ │ ├── test_paa_head.py │ │ ├── test_pisa_head.py │ │ ├── test_sabl_retina_head.py │ │ ├── test_transformer_head.py │ │ ├── test_vfnet_head.py │ │ └── test_yolact_head.py │ ├── test_forward.py │ ├── test_necks.py │ ├── test_roi_heads │ │ ├── __init__.py │ │ ├── test_bbox_head.py │ │ ├── test_mask_head.py │ │ ├── test_roi_extractor.py │ │ ├── test_sabl_bbox_head.py │ │ └── utils.py │ └── test_utils │ │ ├── test_position_encoding.py │ │ └── test_transformer.py ├── test_onnx │ ├── __init__.py │ ├── data │ │ ├── retina_head_get_bboxes.pkl │ │ ├── yolov3_head_get_bboxes.pkl │ │ └── yolov3_neck.pkl │ ├── test_head.py │ ├── test_neck.py │ └── utils.py ├── test_runtime │ ├── async_benchmark.py │ ├── test_async.py │ ├── test_config.py │ ├── test_eval_hook.py │ └── test_fp16.py └── test_utils │ ├── test_anchor.py │ ├── test_assigner.py │ ├── test_coder.py │ ├── test_masks.py │ ├── test_misc.py │ ├── test_version.py │ └── test_visualization.py └── tools ├── analysis_tools ├── analyze_logs.py ├── analyze_results.py ├── benchmark.py ├── coco_error_analysis.py ├── eval_metric.py ├── get_flops.py ├── robustness_eval.py └── test_robustness.py ├── dataset_converters ├── cityscapes.py └── pascal_voc.py ├── deployment ├── mmdet2torchserve.py ├── mmdet_handler.py ├── onnx2tensorrt.py └── pytorch2onnx.py ├── dist_test.sh ├── dist_train.sh ├── misc ├── browse_dataset.py └── print_config.py ├── model_converters ├── detectron2pytorch.py ├── publish_model.py ├── regnet2mmdet.py └── upgrade_model_version.py ├── slurm_test.sh ├── slurm_train.sh ├── test.py └── train.py /.dev_scripts/batch_test.sh: -------------------------------------------------------------------------------- 1 | export PYTHONPATH=${PWD} 2 | 3 | partition=$1 4 | model_dir=$2 5 | json_out=$3 6 | job_name=batch_test 7 | gpus=8 8 | gpu_per_node=8 9 | 10 | touch $json_out 11 | lastLine=$(tail -n 1 $json_out) 12 | while [ "$lastLine" != "finished" ] 13 | do 14 | srun -p ${partition} --gres=gpu:${gpu_per_node} -n${gpus} --ntasks-per-node=${gpu_per_node} \ 15 | --job-name=${job_name} --kill-on-bad-exit=1 \ 16 | python .dev_scripts/batch_test.py $model_dir $json_out --launcher='slurm' 17 | lastLine=$(tail -n 1 $json_out) 18 | echo $lastLine 19 | done 20 | -------------------------------------------------------------------------------- /.dev_scripts/linter.sh: -------------------------------------------------------------------------------- 1 | yapf -r -i mmdet/ configs/ tests/ tools/ 2 | isort -rc mmdet/ configs/ tests/ tools/ 3 | flake8 . 4 | -------------------------------------------------------------------------------- /.github/CONTRIBUTING.md: -------------------------------------------------------------------------------- 1 | We appreciate all contributions to improve MMDetection. Please refer to [CONTRIBUTING.md](https://github.com/open-mmlab/mmcv/blob/master/CONTRIBUTING.md) in MMCV for more details about the contributing guideline. 2 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/config.yml: -------------------------------------------------------------------------------- 1 | blank_issues_enabled: false 2 | 3 | contact_links: 4 | - name: Common Issues 5 | url: https://mmdetection.readthedocs.io/en/latest/faq.html 6 | about: Check if your issue already has solutions 7 | - name: MMDetection Documentation 8 | url: https://mmdetection.readthedocs.io/en/latest/ 9 | about: Check if your question is answered in docs 10 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/feature_request.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: Feature request 3 | about: Suggest an idea for this project 4 | title: '' 5 | labels: '' 6 | assignees: '' 7 | 8 | --- 9 | 10 | **Describe the feature** 11 | 12 | **Motivation** 13 | A clear and concise description of the motivation of the feature. 14 | Ex1. It is inconvenient when [....]. 15 | Ex2. There is a recent paper [....], which is very helpful for [....]. 16 | 17 | **Related resources** 18 | If there is an official code release or third-party implementations, please also provide the information here, which would be very helpful. 19 | 20 | **Additional context** 21 | Add any other context or screenshots about the feature request here. 22 | If you would like to implement the feature and create a PR, please leave a comment here and that would be much appreciated. 23 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/general_questions.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: General questions 3 | about: Ask general questions to get help 4 | title: '' 5 | labels: '' 6 | assignees: '' 7 | 8 | --- 9 | -------------------------------------------------------------------------------- /.github/workflows/build_pat.yml: -------------------------------------------------------------------------------- 1 | name: build_pat 2 | 3 | on: push 4 | 5 | jobs: 6 | build_parrots: 7 | runs-on: ubuntu-latest 8 | container: 9 | image: ghcr.io/sunnyxiaohu/parrots-mmcv:1.2.1 10 | credentials: 11 | username: sunnyxiaohu 12 | password: ${{secrets.CR_PAT}} 13 | 14 | steps: 15 | - uses: actions/checkout@v2 16 | - name: Install mmdet dependencies 17 | run: | 18 | git clone https://github.com/open-mmlab/mmcv.git && cd mmcv 19 | MMCV_WITH_OPS=1 python setup.py install 20 | cd .. && rm -rf mmcv 21 | python -c 'import mmcv; print(mmcv.__version__)' 22 | pip install -r requirements.txt 23 | - name: Build and install 24 | run: rm -rf .eggs && pip install -e . 25 | -------------------------------------------------------------------------------- /.github/workflows/deploy.yml: -------------------------------------------------------------------------------- 1 | name: deploy 2 | 3 | on: push 4 | 5 | jobs: 6 | build-n-publish: 7 | runs-on: ubuntu-latest 8 | if: startsWith(github.event.ref, 'refs/tags') 9 | steps: 10 | - uses: actions/checkout@v2 11 | - name: Set up Python 3.7 12 | uses: actions/setup-python@v2 13 | with: 14 | python-version: 3.7 15 | - name: Install torch 16 | run: pip install torch 17 | - name: Install wheel 18 | run: pip install wheel 19 | - name: Build MMDetection 20 | run: python setup.py sdist bdist_wheel 21 | - name: Publish distribution to PyPI 22 | run: | 23 | pip install twine 24 | twine upload dist/* -u __token__ -p ${{ secrets.pypi_password }} 25 | -------------------------------------------------------------------------------- /.readthedocs.yml: -------------------------------------------------------------------------------- 1 | version: 2 2 | 3 | python: 4 | version: 3.7 5 | install: 6 | - requirements: requirements/docs.txt 7 | - requirements: requirements/readthedocs.txt 8 | -------------------------------------------------------------------------------- /configs/_base_/datasets/lvis_v0.5_instance.py: -------------------------------------------------------------------------------- 1 | _base_ = 'coco_instance.py' 2 | dataset_type = 'LVISV05Dataset' 3 | data_root = 'data/lvis_v0.5/' 4 | data = dict( 5 | samples_per_gpu=2, 6 | workers_per_gpu=2, 7 | train=dict( 8 | _delete_=True, 9 | type='ClassBalancedDataset', 10 | oversample_thr=1e-3, 11 | dataset=dict( 12 | type=dataset_type, 13 | ann_file=data_root + 'annotations/lvis_v0.5_train.json', 14 | img_prefix=data_root + 'train2017/')), 15 | val=dict( 16 | type=dataset_type, 17 | ann_file=data_root + 'annotations/lvis_v0.5_val.json', 18 | img_prefix=data_root + 'val2017/'), 19 | test=dict( 20 | type=dataset_type, 21 | ann_file=data_root + 'annotations/lvis_v0.5_val.json', 22 | img_prefix=data_root + 'val2017/')) 23 | evaluation = dict(metric=['bbox', 'segm']) 24 | -------------------------------------------------------------------------------- /configs/_base_/datasets/lvis_v1_instance.py: -------------------------------------------------------------------------------- 1 | _base_ = 'coco_instance.py' 2 | dataset_type = 'LVISV1Dataset' 3 | data_root = 'data/lvis_v1/' 4 | data = dict( 5 | samples_per_gpu=2, 6 | workers_per_gpu=2, 7 | train=dict( 8 | _delete_=True, 9 | type='ClassBalancedDataset', 10 | oversample_thr=1e-3, 11 | dataset=dict( 12 | type=dataset_type, 13 | ann_file=data_root + 'annotations/lvis_v1_train.json', 14 | img_prefix=data_root)), 15 | val=dict( 16 | type=dataset_type, 17 | ann_file=data_root + 'annotations/lvis_v1_val.json', 18 | img_prefix=data_root), 19 | test=dict( 20 | type=dataset_type, 21 | ann_file=data_root + 'annotations/lvis_v1_val.json', 22 | img_prefix=data_root)) 23 | evaluation = dict(metric=['bbox', 'segm']) 24 | -------------------------------------------------------------------------------- /configs/_base_/default_runtime.py: -------------------------------------------------------------------------------- 1 | checkpoint_config = dict(interval=1) 2 | # yapf:disable 3 | log_config = dict( 4 | interval=50, 5 | hooks=[ 6 | dict(type='TextLoggerHook'), 7 | # dict(type='TensorboardLoggerHook') 8 | ]) 9 | # yapf:enable 10 | custom_hooks = [dict(type='NumClassCheckHook')] 11 | 12 | dist_params = dict(backend='nccl') 13 | log_level = 'INFO' 14 | load_from = None 15 | resume_from = None 16 | workflow = [('train', 1)] 17 | -------------------------------------------------------------------------------- /configs/_base_/schedules/schedule_1x.py: -------------------------------------------------------------------------------- 1 | # optimizer 2 | optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 3 | optimizer_config = dict(grad_clip=None) 4 | # learning policy 5 | lr_config = dict( 6 | policy='step', 7 | warmup='linear', 8 | warmup_iters=500, 9 | warmup_ratio=0.001, 10 | step=[8, 11]) 11 | runner = dict(type='EpochBasedRunner', max_epochs=12) 12 | -------------------------------------------------------------------------------- /configs/_base_/schedules/schedule_20e.py: -------------------------------------------------------------------------------- 1 | # optimizer 2 | optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 3 | optimizer_config = dict(grad_clip=None) 4 | # learning policy 5 | lr_config = dict( 6 | policy='step', 7 | warmup='linear', 8 | warmup_iters=500, 9 | warmup_ratio=0.001, 10 | step=[16, 19]) 11 | runner = dict(type='EpochBasedRunner', max_epochs=20) 12 | -------------------------------------------------------------------------------- /configs/_base_/schedules/schedule_2x.py: -------------------------------------------------------------------------------- 1 | # optimizer 2 | optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 3 | optimizer_config = dict(grad_clip=None) 4 | # learning policy 5 | lr_config = dict( 6 | policy='step', 7 | warmup='linear', 8 | warmup_iters=500, 9 | warmup_ratio=0.001, 10 | step=[16, 22]) 11 | runner = dict(type='EpochBasedRunner', max_epochs=24) 12 | -------------------------------------------------------------------------------- /configs/atss/atss_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './atss_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='torchvision://resnet101', 4 | backbone=dict(depth=101), 5 | ) 6 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_mask_rcnn_r101_caffe_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_mask_rcnn_r50_caffe_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://detectron2/resnet101_caffe', 4 | backbone=dict(depth=101)) 5 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_mask_rcnn_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_mask_rcnn_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_mask_rcnn_r101_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_mask_rcnn_r50_fpn_20e_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/cascade_mask_rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_instance.py', 4 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/cascade_mask_rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_instance.py', 4 | '../_base_/schedules/schedule_20e.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_mask_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_mask_rcnn_r50_fpn_20e_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_mask_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_mask_rcnn_r50_fpn_20e_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_rcnn_r101_caffe_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_rcnn_r50_caffe_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://detectron2/resnet101_caffe', 4 | backbone=dict(depth=101)) 5 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_rcnn_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_rcnn_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_rcnn_r101_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_rcnn_r50_fpn_20e_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/cascade_rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_detection.py', 4 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_rcnn_r50_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_rcnn_r50_fpn_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 19]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=20) 5 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_rcnn_x101_32x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_rcnn_x101_32x4d_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_rcnn_r50_fpn_20e_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_rcnn_x101_64x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | type='CascadeRCNN', 4 | pretrained='open-mmlab://resnext101_64x4d', 5 | backbone=dict( 6 | type='ResNeXt', 7 | depth=101, 8 | groups=64, 9 | base_width=4, 10 | num_stages=4, 11 | out_indices=(0, 1, 2, 3), 12 | frozen_stages=1, 13 | norm_cfg=dict(type='BN', requires_grad=True), 14 | style='pytorch')) 15 | -------------------------------------------------------------------------------- /configs/cascade_rcnn/cascade_rcnn_x101_64x4d_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_rcnn_r50_fpn_20e_coco.py' 2 | model = dict( 3 | type='CascadeRCNN', 4 | pretrained='open-mmlab://resnext101_64x4d', 5 | backbone=dict( 6 | type='ResNeXt', 7 | depth=101, 8 | groups=64, 9 | base_width=4, 10 | num_stages=4, 11 | out_indices=(0, 1, 2, 3), 12 | frozen_stages=1, 13 | norm_cfg=dict(type='BN', requires_grad=True), 14 | style='pytorch')) 15 | -------------------------------------------------------------------------------- /configs/dcn/cascade_mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../cascade_rcnn/cascade_mask_rcnn_r101_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 5 | stage_with_dcn=(False, True, True, True))) 6 | -------------------------------------------------------------------------------- /configs/dcn/cascade_mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 5 | stage_with_dcn=(False, True, True, True))) 6 | -------------------------------------------------------------------------------- /configs/dcn/cascade_mask_rcnn_x101_32x4d_fpn_dconv_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 5 | stage_with_dcn=(False, True, True, True))) 6 | -------------------------------------------------------------------------------- /configs/dcn/cascade_rcnn_r101_fpn_dconv_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../cascade_rcnn/cascade_rcnn_r101_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 5 | stage_with_dcn=(False, True, True, True))) 6 | -------------------------------------------------------------------------------- /configs/dcn/cascade_rcnn_r50_fpn_dconv_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 5 | stage_with_dcn=(False, True, True, True))) 6 | -------------------------------------------------------------------------------- /configs/dcn/faster_rcnn_r101_fpn_dconv_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r101_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 5 | stage_with_dcn=(False, True, True, True))) 6 | -------------------------------------------------------------------------------- /configs/dcn/faster_rcnn_r50_fpn_dconv_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 5 | stage_with_dcn=(False, True, True, True))) 6 | -------------------------------------------------------------------------------- /configs/dcn/faster_rcnn_r50_fpn_dpool_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | roi_head=dict( 4 | bbox_roi_extractor=dict( 5 | type='SingleRoIExtractor', 6 | roi_layer=dict( 7 | _delete_=True, 8 | type='DeformRoIPoolPack', 9 | output_size=7, 10 | output_channels=256), 11 | out_channels=256, 12 | featmap_strides=[4, 8, 16, 32]))) 13 | -------------------------------------------------------------------------------- /configs/dcn/faster_rcnn_r50_fpn_mdconv_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False), 5 | stage_with_dcn=(False, True, True, True))) 6 | -------------------------------------------------------------------------------- /configs/dcn/faster_rcnn_r50_fpn_mdconv_c3-c5_group4_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | dcn=dict(type='DCNv2', deform_groups=4, fallback_on_stride=False), 5 | stage_with_dcn=(False, True, True, True))) 6 | -------------------------------------------------------------------------------- /configs/dcn/faster_rcnn_r50_fpn_mdpool_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | roi_head=dict( 4 | bbox_roi_extractor=dict( 5 | type='SingleRoIExtractor', 6 | roi_layer=dict( 7 | _delete_=True, 8 | type='ModulatedDeformRoIPoolPack', 9 | output_size=7, 10 | output_channels=256), 11 | out_channels=256, 12 | featmap_strides=[4, 8, 16, 32]))) 13 | -------------------------------------------------------------------------------- /configs/dcn/faster_rcnn_x101_32x4d_fpn_dconv_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch', 14 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 15 | stage_with_dcn=(False, True, True, True))) 16 | -------------------------------------------------------------------------------- /configs/dcn/mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r101_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 5 | stage_with_dcn=(False, True, True, True))) 6 | -------------------------------------------------------------------------------- /configs/dcn/mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 5 | stage_with_dcn=(False, True, True, True))) 6 | -------------------------------------------------------------------------------- /configs/dcn/mask_rcnn_r50_fpn_mdconv_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False), 5 | stage_with_dcn=(False, True, True, True))) 6 | -------------------------------------------------------------------------------- /configs/deepfashion/mask_rcnn_r50_fpn_15e_deepfashion.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/mask_rcnn_r50_fpn.py', 3 | '../_base_/datasets/deepfashion.py', '../_base_/schedules/schedule_1x.py', 4 | '../_base_/default_runtime.py' 5 | ] 6 | model = dict( 7 | roi_head=dict( 8 | bbox_head=dict(num_classes=15), mask_head=dict(num_classes=15))) 9 | # runtime settings 10 | runner = dict(type='EpochBasedRunner', max_epochs=15) 11 | -------------------------------------------------------------------------------- /configs/detectors/cascade_rcnn_r50_rfp_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/cascade_rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_detection.py', 4 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 5 | ] 6 | 7 | model = dict( 8 | backbone=dict( 9 | type='DetectoRS_ResNet', 10 | conv_cfg=dict(type='ConvAWS'), 11 | output_img=True), 12 | neck=dict( 13 | type='RFP', 14 | rfp_steps=2, 15 | aspp_out_channels=64, 16 | aspp_dilations=(1, 3, 6, 1), 17 | rfp_backbone=dict( 18 | rfp_inplanes=256, 19 | type='DetectoRS_ResNet', 20 | depth=50, 21 | num_stages=4, 22 | out_indices=(0, 1, 2, 3), 23 | frozen_stages=1, 24 | norm_cfg=dict(type='BN', requires_grad=True), 25 | norm_eval=True, 26 | conv_cfg=dict(type='ConvAWS'), 27 | pretrained='torchvision://resnet50', 28 | style='pytorch'))) 29 | -------------------------------------------------------------------------------- /configs/detectors/cascade_rcnn_r50_sac_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/cascade_rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_detection.py', 4 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 5 | ] 6 | 7 | model = dict( 8 | backbone=dict( 9 | type='DetectoRS_ResNet', 10 | conv_cfg=dict(type='ConvAWS'), 11 | sac=dict(type='SAC', use_deform=True), 12 | stage_with_sac=(False, True, True, True))) 13 | -------------------------------------------------------------------------------- /configs/detectors/htc_r50_rfp_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../htc/htc_r50_fpn_1x_coco.py' 2 | 3 | model = dict( 4 | backbone=dict( 5 | type='DetectoRS_ResNet', 6 | conv_cfg=dict(type='ConvAWS'), 7 | output_img=True), 8 | neck=dict( 9 | type='RFP', 10 | rfp_steps=2, 11 | aspp_out_channels=64, 12 | aspp_dilations=(1, 3, 6, 1), 13 | rfp_backbone=dict( 14 | rfp_inplanes=256, 15 | type='DetectoRS_ResNet', 16 | depth=50, 17 | num_stages=4, 18 | out_indices=(0, 1, 2, 3), 19 | frozen_stages=1, 20 | norm_cfg=dict(type='BN', requires_grad=True), 21 | norm_eval=True, 22 | conv_cfg=dict(type='ConvAWS'), 23 | pretrained='torchvision://resnet50', 24 | style='pytorch'))) 25 | -------------------------------------------------------------------------------- /configs/detectors/htc_r50_sac_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../htc/htc_r50_fpn_1x_coco.py' 2 | 3 | model = dict( 4 | backbone=dict( 5 | type='DetectoRS_ResNet', 6 | conv_cfg=dict(type='ConvAWS'), 7 | sac=dict(type='SAC', use_deform=True), 8 | stage_with_sac=(False, True, True, True))) 9 | -------------------------------------------------------------------------------- /configs/double_heads/dh_faster_rcnn_r50_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | roi_head=dict( 4 | type='DoubleHeadRoIHead', 5 | reg_roi_scale_factor=1.3, 6 | bbox_head=dict( 7 | _delete_=True, 8 | type='DoubleConvFCBBoxHead', 9 | num_convs=4, 10 | num_fcs=2, 11 | in_channels=256, 12 | conv_out_channels=1024, 13 | fc_out_channels=1024, 14 | roi_feat_size=7, 15 | num_classes=80, 16 | bbox_coder=dict( 17 | type='DeltaXYWHBBoxCoder', 18 | target_means=[0., 0., 0., 0.], 19 | target_stds=[0.1, 0.1, 0.2, 0.2]), 20 | reg_class_agnostic=False, 21 | loss_cls=dict( 22 | type='CrossEntropyLoss', use_sigmoid=False, loss_weight=2.0), 23 | loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=2.0)))) 24 | -------------------------------------------------------------------------------- /configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict(plugins=[ 4 | dict( 5 | cfg=dict( 6 | type='GeneralizedAttention', 7 | spatial_range=-1, 8 | num_heads=8, 9 | attention_type='0010', 10 | kv_stride=2), 11 | stages=(False, False, True, True), 12 | position='after_conv2') 13 | ])) 14 | -------------------------------------------------------------------------------- /configs/empirical_attention/faster_rcnn_r50_fpn_attention_0010_dcn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | plugins=[ 5 | dict( 6 | cfg=dict( 7 | type='GeneralizedAttention', 8 | spatial_range=-1, 9 | num_heads=8, 10 | attention_type='0010', 11 | kv_stride=2), 12 | stages=(False, False, True, True), 13 | position='after_conv2') 14 | ], 15 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 16 | stage_with_dcn=(False, True, True, True))) 17 | -------------------------------------------------------------------------------- /configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict(plugins=[ 4 | dict( 5 | cfg=dict( 6 | type='GeneralizedAttention', 7 | spatial_range=-1, 8 | num_heads=8, 9 | attention_type='1111', 10 | kv_stride=2), 11 | stages=(False, False, True, True), 12 | position='after_conv2') 13 | ])) 14 | -------------------------------------------------------------------------------- /configs/empirical_attention/faster_rcnn_r50_fpn_attention_1111_dcn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | plugins=[ 5 | dict( 6 | cfg=dict( 7 | type='GeneralizedAttention', 8 | spatial_range=-1, 9 | num_heads=8, 10 | attention_type='1111', 11 | kv_stride=2), 12 | stages=(False, False, True, True), 13 | position='after_conv2') 14 | ], 15 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 16 | stage_with_dcn=(False, True, True, True))) 17 | -------------------------------------------------------------------------------- /configs/fast_rcnn/README.md: -------------------------------------------------------------------------------- 1 | # Fast R-CNN 2 | 3 | ## Introduction 4 | 5 | [ALGORITHM] 6 | 7 | ```latex 8 | @inproceedings{girshick2015fast, 9 | title={Fast r-cnn}, 10 | author={Girshick, Ross}, 11 | booktitle={Proceedings of the IEEE international conference on computer vision}, 12 | year={2015} 13 | } 14 | ``` 15 | 16 | ## Results and models 17 | -------------------------------------------------------------------------------- /configs/fast_rcnn/fast_rcnn_r101_caffe_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fast_rcnn_r50_caffe_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://detectron2/resnet101_caffe', 4 | backbone=dict(depth=101)) 5 | -------------------------------------------------------------------------------- /configs/fast_rcnn/fast_rcnn_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fast_rcnn_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/fast_rcnn/fast_rcnn_r101_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fast_rcnn_r50_fpn_2x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/fast_rcnn/fast_rcnn_r50_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fast_rcnn_r50_fpn_1x_coco.py' 2 | 3 | # learning policy 4 | lr_config = dict(step=[16, 22]) 5 | runner = dict(type='EpochBasedRunner', max_epochs=24) 6 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r101_caffe_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_caffe_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://detectron2/resnet101_caffe', 4 | backbone=dict(depth=101)) 5 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r101_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_fpn_2x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r50_caffe_dc5_mstrain_3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_caffe_dc5_mstrain_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[28, 34]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=36) 5 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_1x_coco-person-bicycle-car.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_caffe_fpn_mstrain_1x_coco.py' 2 | model = dict(roi_head=dict(bbox_head=dict(num_classes=3))) 3 | classes = ('person', 'bicycle', 'car') 4 | data = dict( 5 | train=dict(classes=classes), 6 | val=dict(classes=classes), 7 | test=dict(classes=classes)) 8 | 9 | load_from = 'http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco_bbox_mAP-0.398_20200504_163323-30042637.pth' # noqa 10 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_1x_coco-person.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_caffe_fpn_mstrain_1x_coco.py' 2 | model = dict(roi_head=dict(bbox_head=dict(num_classes=1))) 3 | classes = ('person', ) 4 | data = dict( 5 | train=dict(classes=classes), 6 | val=dict(classes=classes), 7 | test=dict(classes=classes)) 8 | 9 | load_from = 'http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco_bbox_mAP-0.398_20200504_163323-30042637.pth' # noqa 10 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_caffe_fpn_mstrain_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 23]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_caffe_fpn_mstrain_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[28, 34]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=36) 5 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_mstrain_90k_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = 'faster_rcnn_r50_caffe_fpn_mstrain_1x_coco.py' 2 | 3 | # learning policy 4 | lr_config = dict( 5 | policy='step', 6 | warmup='linear', 7 | warmup_iters=500, 8 | warmup_ratio=0.001, 9 | step=[60000, 80000]) 10 | 11 | # Runner type 12 | runner = dict(_delete_=True, type='IterBasedRunner', max_iters=90000) 13 | 14 | checkpoint_config = dict(interval=10000) 15 | evaluation = dict(interval=10000, metric='bbox') 16 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/faster_rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_detection.py', 4 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r50_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/faster_rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_detection.py', 4 | '../_base_/schedules/schedule_2x.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r50_fpn_bounded_iou_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | roi_head=dict( 4 | bbox_head=dict( 5 | reg_decoded_bbox=True, 6 | loss_bbox=dict(type='BoundedIoULoss', loss_weight=10.0)))) 7 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r50_fpn_giou_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | roi_head=dict( 4 | bbox_head=dict( 5 | reg_decoded_bbox=True, 6 | loss_bbox=dict(type='GIoULoss', loss_weight=10.0)))) 7 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r50_fpn_iou_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | roi_head=dict( 4 | bbox_head=dict( 5 | reg_decoded_bbox=True, 6 | loss_bbox=dict(type='IoULoss', loss_weight=10.0)))) 7 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r50_fpn_ohem_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict(train_cfg=dict(rcnn=dict(sampler=dict(type='OHEMSampler')))) 3 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_r50_fpn_soft_nms_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/faster_rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_detection.py', 4 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 5 | ] 6 | 7 | model = dict( 8 | test_cfg=dict( 9 | rcnn=dict( 10 | score_thr=0.05, 11 | nms=dict(type='soft_nms', iou_threshold=0.5), 12 | max_per_img=100))) 13 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_x101_32x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_x101_32x4d_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_fpn_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_x101_64x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/faster_rcnn/faster_rcnn_x101_64x4d_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_fpn_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/fcos/fcos_center_r50_caffe_fpn_gn-head_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fcos_r50_caffe_fpn_gn-head_1x_coco.py' 2 | model = dict(bbox_head=dict(center_sampling=True, center_sample_radius=1.5)) 3 | -------------------------------------------------------------------------------- /configs/fcos/fcos_r101_caffe_fpn_gn-head_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fcos_r50_caffe_fpn_gn-head_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://detectron/resnet101_caffe', 4 | backbone=dict(depth=101)) 5 | -------------------------------------------------------------------------------- /configs/fcos/fcos_r50_caffe_fpn_gn-head_4x4_1x_coco.py: -------------------------------------------------------------------------------- 1 | # TODO: Remove this config after benchmarking all related configs 2 | _base_ = 'fcos_r50_caffe_fpn_gn-head_1x_coco.py' 3 | 4 | data = dict(samples_per_gpu=4, workers_per_gpu=4) 5 | -------------------------------------------------------------------------------- /configs/foveabox/fovea_align_r101_fpn_gn-head_4x4_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fovea_r50_fpn_4x4_1x_coco.py' 2 | model = dict( 3 | pretrained='torchvision://resnet101', 4 | backbone=dict(depth=101), 5 | bbox_head=dict( 6 | with_deform=True, 7 | norm_cfg=dict(type='GN', num_groups=32, requires_grad=True))) 8 | # learning policy 9 | lr_config = dict(step=[16, 22]) 10 | runner = dict(type='EpochBasedRunner', max_epochs=24) 11 | -------------------------------------------------------------------------------- /configs/foveabox/fovea_align_r50_fpn_gn-head_4x4_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fovea_r50_fpn_4x4_1x_coco.py' 2 | model = dict( 3 | bbox_head=dict( 4 | with_deform=True, 5 | norm_cfg=dict(type='GN', num_groups=32, requires_grad=True))) 6 | # learning policy 7 | lr_config = dict(step=[16, 22]) 8 | runner = dict(type='EpochBasedRunner', max_epochs=24) 9 | optimizer_config = dict( 10 | _delete_=True, grad_clip=dict(max_norm=35, norm_type=2)) 11 | -------------------------------------------------------------------------------- /configs/foveabox/fovea_r101_fpn_4x4_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fovea_r50_fpn_4x4_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/foveabox/fovea_r101_fpn_4x4_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fovea_r50_fpn_4x4_2x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/foveabox/fovea_r50_fpn_4x4_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fovea_r50_fpn_4x4_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 22]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/fp16/faster_rcnn_r50_fpn_fp16_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | # fp16 settings 3 | fp16 = dict(loss_scale=512.) 4 | -------------------------------------------------------------------------------- /configs/fp16/mask_rcnn_r50_fpn_fp16_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py' 2 | # fp16 settings 3 | fp16 = dict(loss_scale=512.) 4 | -------------------------------------------------------------------------------- /configs/fp16/retinanet_r50_fpn_fp16_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../retinanet/retinanet_r50_fpn_1x_coco.py' 2 | # fp16 settings 3 | fp16 = dict(loss_scale=512.) 4 | -------------------------------------------------------------------------------- /configs/fpg/faster_rcnn_r50_fpg-chn128_crop640_50e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = 'faster_rcnn_r50_fpg_crop640_50e_coco.py' 2 | 3 | norm_cfg = dict(type='BN', requires_grad=True) 4 | model = dict( 5 | neck=dict(out_channels=128, inter_channels=128), 6 | rpn_head=dict(in_channels=128), 7 | roi_head=dict( 8 | bbox_roi_extractor=dict(out_channels=128), 9 | bbox_head=dict(in_channels=128))) 10 | -------------------------------------------------------------------------------- /configs/fpg/mask_rcnn_r50_fpg-chn128_crop640_50e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = 'mask_rcnn_r50_fpg_crop640_50e_coco.py' 2 | 3 | model = dict( 4 | neck=dict(out_channels=128, inter_channels=128), 5 | rpn_head=dict(in_channels=128), 6 | roi_head=dict( 7 | bbox_roi_extractor=dict(out_channels=128), 8 | bbox_head=dict(in_channels=128), 9 | mask_roi_extractor=dict(out_channels=128), 10 | mask_head=dict(in_channels=128))) 11 | -------------------------------------------------------------------------------- /configs/fpg/retinanet_r50_fpg-chn128_crop640_50e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = 'retinanet_r50_fpg_crop640_50e_coco.py' 2 | 3 | model = dict( 4 | neck=dict(out_channels=128, inter_channels=128), 5 | bbox_head=dict(in_channels=128)) 6 | -------------------------------------------------------------------------------- /configs/free_anchor/retinanet_free_anchor_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_free_anchor_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/free_anchor/retinanet_free_anchor_r50_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../retinanet/retinanet_r50_fpn_1x_coco.py' 2 | model = dict( 3 | bbox_head=dict( 4 | _delete_=True, 5 | type='FreeAnchorRetinaHead', 6 | num_classes=80, 7 | in_channels=256, 8 | stacked_convs=4, 9 | feat_channels=256, 10 | anchor_generator=dict( 11 | type='AnchorGenerator', 12 | octave_base_scale=4, 13 | scales_per_octave=3, 14 | ratios=[0.5, 1.0, 2.0], 15 | strides=[8, 16, 32, 64, 128]), 16 | bbox_coder=dict( 17 | type='DeltaXYWHBBoxCoder', 18 | target_means=[.0, .0, .0, .0], 19 | target_stds=[0.1, 0.1, 0.2, 0.2]), 20 | loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.75))) 21 | optimizer_config = dict( 22 | _delete_=True, grad_clip=dict(max_norm=35, norm_type=2)) 23 | -------------------------------------------------------------------------------- /configs/free_anchor/retinanet_free_anchor_x101_32x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_free_anchor_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | style='pytorch')) 13 | -------------------------------------------------------------------------------- /configs/fsaf/fsaf_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fsaf_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/fsaf/fsaf_x101_64x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fsaf_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/gcnet/cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), norm_eval=False)) 5 | -------------------------------------------------------------------------------- /configs/gcnet/cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_dconv_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../dcn/cascade_mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), norm_eval=False)) 5 | -------------------------------------------------------------------------------- /configs/gcnet/cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_dconv_c3-c5_r16_gcb_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../dcn/cascade_rcnn_r50_fpn_dconv_c3-c5_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), 5 | norm_eval=False, 6 | plugins=[ 7 | dict( 8 | cfg=dict(type='ContextBlock', ratio=1. / 16), 9 | stages=(False, True, True, True), 10 | position='after_conv3') 11 | ])) 12 | -------------------------------------------------------------------------------- /configs/gcnet/cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_dconv_c3-c5_r4_gcb_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../dcn/cascade_mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), 5 | norm_eval=False, 6 | plugins=[ 7 | dict( 8 | cfg=dict(type='ContextBlock', ratio=1. / 4), 9 | stages=(False, True, True, True), 10 | position='after_conv3') 11 | ])) 12 | -------------------------------------------------------------------------------- /configs/gcnet/cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_r16_gcb_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), 5 | norm_eval=False, 6 | plugins=[ 7 | dict( 8 | cfg=dict(type='ContextBlock', ratio=1. / 16), 9 | stages=(False, True, True, True), 10 | position='after_conv3') 11 | ])) 12 | -------------------------------------------------------------------------------- /configs/gcnet/cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), 5 | norm_eval=False, 6 | plugins=[ 7 | dict( 8 | cfg=dict(type='ContextBlock', ratio=1. / 4), 9 | stages=(False, True, True, True), 10 | position='after_conv3') 11 | ])) 12 | -------------------------------------------------------------------------------- /configs/gcnet/mask_rcnn_r101_fpn_r16_gcb_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r101_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict(plugins=[ 4 | dict( 5 | cfg=dict(type='ContextBlock', ratio=1. / 16), 6 | stages=(False, True, True, True), 7 | position='after_conv3') 8 | ])) 9 | -------------------------------------------------------------------------------- /configs/gcnet/mask_rcnn_r101_fpn_r4_gcb_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r101_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict(plugins=[ 4 | dict( 5 | cfg=dict(type='ContextBlock', ratio=1. / 4), 6 | stages=(False, True, True, True), 7 | position='after_conv3') 8 | ])) 9 | -------------------------------------------------------------------------------- /configs/gcnet/mask_rcnn_r101_fpn_syncbn-backbone_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r101_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), norm_eval=False)) 5 | -------------------------------------------------------------------------------- /configs/gcnet/mask_rcnn_r101_fpn_syncbn-backbone_r16_gcb_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r101_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), 5 | norm_eval=False, 6 | plugins=[ 7 | dict( 8 | cfg=dict(type='ContextBlock', ratio=1. / 16), 9 | stages=(False, True, True, True), 10 | position='after_conv3') 11 | ])) 12 | -------------------------------------------------------------------------------- /configs/gcnet/mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r101_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), 5 | norm_eval=False, 6 | plugins=[ 7 | dict( 8 | cfg=dict(type='ContextBlock', ratio=1. / 4), 9 | stages=(False, True, True, True), 10 | position='after_conv3') 11 | ])) 12 | -------------------------------------------------------------------------------- /configs/gcnet/mask_rcnn_r50_fpn_r16_gcb_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict(plugins=[ 4 | dict( 5 | cfg=dict(type='ContextBlock', ratio=1. / 16), 6 | stages=(False, True, True, True), 7 | position='after_conv3') 8 | ])) 9 | -------------------------------------------------------------------------------- /configs/gcnet/mask_rcnn_r50_fpn_r4_gcb_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict(plugins=[ 4 | dict( 5 | cfg=dict(type='ContextBlock', ratio=1. / 4), 6 | stages=(False, True, True, True), 7 | position='after_conv3') 8 | ])) 9 | -------------------------------------------------------------------------------- /configs/gcnet/mask_rcnn_r50_fpn_syncbn-backbone_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), norm_eval=False)) 5 | -------------------------------------------------------------------------------- /configs/gcnet/mask_rcnn_r50_fpn_syncbn-backbone_r16_gcb_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), 5 | norm_eval=False, 6 | plugins=[ 7 | dict( 8 | cfg=dict(type='ContextBlock', ratio=1. / 16), 9 | stages=(False, True, True, True), 10 | position='after_conv3') 11 | ])) 12 | -------------------------------------------------------------------------------- /configs/gcnet/mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), 5 | norm_eval=False, 6 | plugins=[ 7 | dict( 8 | cfg=dict(type='ContextBlock', ratio=1. / 4), 9 | stages=(False, True, True, True), 10 | position='after_conv3') 11 | ])) 12 | -------------------------------------------------------------------------------- /configs/gcnet/mask_rcnn_x101_32x4d_fpn_syncbn-backbone_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_x101_32x4d_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), norm_eval=False)) 5 | -------------------------------------------------------------------------------- /configs/gcnet/mask_rcnn_x101_32x4d_fpn_syncbn-backbone_r16_gcb_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_x101_32x4d_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), 5 | norm_eval=False, 6 | plugins=[ 7 | dict( 8 | cfg=dict(type='ContextBlock', ratio=1. / 16), 9 | stages=(False, True, True, True), 10 | position='after_conv3') 11 | ])) 12 | -------------------------------------------------------------------------------- /configs/gcnet/mask_rcnn_x101_32x4d_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_x101_32x4d_fpn_1x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | norm_cfg=dict(type='SyncBN', requires_grad=True), 5 | norm_eval=False, 6 | plugins=[ 7 | dict( 8 | cfg=dict(type='ContextBlock', ratio=1. / 4), 9 | stages=(False, True, True, True), 10 | position='after_conv3') 11 | ])) 12 | -------------------------------------------------------------------------------- /configs/gfl/gfl_r101_fpn_dconv_c3-c5_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './gfl_r50_fpn_mstrain_2x_coco.py' 2 | model = dict( 3 | pretrained='torchvision://resnet101', 4 | backbone=dict( 5 | type='ResNet', 6 | depth=101, 7 | num_stages=4, 8 | out_indices=(0, 1, 2, 3), 9 | frozen_stages=1, 10 | norm_cfg=dict(type='BN', requires_grad=True), 11 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 12 | stage_with_dcn=(False, True, True, True), 13 | norm_eval=True, 14 | style='pytorch')) 15 | -------------------------------------------------------------------------------- /configs/gfl/gfl_r101_fpn_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './gfl_r50_fpn_mstrain_2x_coco.py' 2 | model = dict( 3 | pretrained='torchvision://resnet101', 4 | backbone=dict( 5 | type='ResNet', 6 | depth=101, 7 | num_stages=4, 8 | out_indices=(0, 1, 2, 3), 9 | frozen_stages=1, 10 | norm_cfg=dict(type='BN', requires_grad=True), 11 | norm_eval=True, 12 | style='pytorch')) 13 | -------------------------------------------------------------------------------- /configs/gfl/gfl_r50_fpn_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './gfl_r50_fpn_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 22]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | # multi-scale training 6 | img_norm_cfg = dict( 7 | mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) 8 | train_pipeline = [ 9 | dict(type='LoadImageFromFile'), 10 | dict(type='LoadAnnotations', with_bbox=True), 11 | dict( 12 | type='Resize', 13 | img_scale=[(1333, 480), (1333, 800)], 14 | multiscale_mode='range', 15 | keep_ratio=True), 16 | dict(type='RandomFlip', flip_ratio=0.5), 17 | dict(type='Normalize', **img_norm_cfg), 18 | dict(type='Pad', size_divisor=32), 19 | dict(type='DefaultFormatBundle'), 20 | dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']), 21 | ] 22 | data = dict(train=dict(pipeline=train_pipeline)) 23 | -------------------------------------------------------------------------------- /configs/gfl/gfl_x101_32x4d_fpn_dconv_c4-c5_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './gfl_r50_fpn_mstrain_2x_coco.py' 2 | model = dict( 3 | type='GFL', 4 | pretrained='open-mmlab://resnext101_32x4d', 5 | backbone=dict( 6 | type='ResNeXt', 7 | depth=101, 8 | groups=32, 9 | base_width=4, 10 | num_stages=4, 11 | out_indices=(0, 1, 2, 3), 12 | frozen_stages=1, 13 | norm_cfg=dict(type='BN', requires_grad=True), 14 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 15 | stage_with_dcn=(False, False, True, True), 16 | norm_eval=True, 17 | style='pytorch')) 18 | -------------------------------------------------------------------------------- /configs/gfl/gfl_x101_32x4d_fpn_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './gfl_r50_fpn_mstrain_2x_coco.py' 2 | model = dict( 3 | type='GFL', 4 | pretrained='open-mmlab://resnext101_32x4d', 5 | backbone=dict( 6 | type='ResNeXt', 7 | depth=101, 8 | groups=32, 9 | base_width=4, 10 | num_stages=4, 11 | out_indices=(0, 1, 2, 3), 12 | frozen_stages=1, 13 | norm_cfg=dict(type='BN', requires_grad=True), 14 | norm_eval=True, 15 | style='pytorch')) 16 | -------------------------------------------------------------------------------- /configs/ghm/retinanet_ghm_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_ghm_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/ghm/retinanet_ghm_r50_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../retinanet/retinanet_r50_fpn_1x_coco.py' 2 | model = dict( 3 | bbox_head=dict( 4 | loss_cls=dict( 5 | _delete_=True, 6 | type='GHMC', 7 | bins=30, 8 | momentum=0.75, 9 | use_sigmoid=True, 10 | loss_weight=1.0), 11 | loss_bbox=dict( 12 | _delete_=True, 13 | type='GHMR', 14 | mu=0.02, 15 | bins=10, 16 | momentum=0.7, 17 | loss_weight=10.0))) 18 | optimizer_config = dict( 19 | _delete_=True, grad_clip=dict(max_norm=35, norm_type=2)) 20 | -------------------------------------------------------------------------------- /configs/ghm/retinanet_ghm_x101_32x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_ghm_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/ghm/retinanet_ghm_x101_64x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_ghm_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/gn+ws/faster_rcnn_r101_fpn_gn_ws-all_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_fpn_gn_ws-all_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://jhu/resnet101_gn_ws', backbone=dict(depth=101)) 4 | -------------------------------------------------------------------------------- /configs/gn+ws/faster_rcnn_r50_fpn_gn_ws-all_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | conv_cfg = dict(type='ConvWS') 3 | norm_cfg = dict(type='GN', num_groups=32, requires_grad=True) 4 | model = dict( 5 | pretrained='open-mmlab://jhu/resnet50_gn_ws', 6 | backbone=dict(conv_cfg=conv_cfg, norm_cfg=norm_cfg), 7 | neck=dict(conv_cfg=conv_cfg, norm_cfg=norm_cfg), 8 | roi_head=dict( 9 | bbox_head=dict( 10 | type='Shared4Conv1FCBBoxHead', 11 | conv_out_channels=256, 12 | conv_cfg=conv_cfg, 13 | norm_cfg=norm_cfg))) 14 | -------------------------------------------------------------------------------- /configs/gn+ws/faster_rcnn_x101_32x4d_fpn_gn_ws-all_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_fpn_gn_ws-all_1x_coco.py' 2 | conv_cfg = dict(type='ConvWS') 3 | norm_cfg = dict(type='GN', num_groups=32, requires_grad=True) 4 | model = dict( 5 | pretrained='open-mmlab://jhu/resnext101_32x4d_gn_ws', 6 | backbone=dict( 7 | type='ResNeXt', 8 | depth=101, 9 | groups=32, 10 | base_width=4, 11 | num_stages=4, 12 | out_indices=(0, 1, 2, 3), 13 | frozen_stages=1, 14 | style='pytorch', 15 | conv_cfg=conv_cfg, 16 | norm_cfg=norm_cfg)) 17 | -------------------------------------------------------------------------------- /configs/gn+ws/faster_rcnn_x50_32x4d_fpn_gn_ws-all_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_r50_fpn_gn_ws-all_1x_coco.py' 2 | conv_cfg = dict(type='ConvWS') 3 | norm_cfg = dict(type='GN', num_groups=32, requires_grad=True) 4 | model = dict( 5 | pretrained='open-mmlab://jhu/resnext50_32x4d_gn_ws', 6 | backbone=dict( 7 | type='ResNeXt', 8 | depth=50, 9 | groups=32, 10 | base_width=4, 11 | num_stages=4, 12 | out_indices=(0, 1, 2, 3), 13 | frozen_stages=1, 14 | style='pytorch', 15 | conv_cfg=conv_cfg, 16 | norm_cfg=norm_cfg)) 17 | -------------------------------------------------------------------------------- /configs/gn+ws/mask_rcnn_r101_fpn_gn_ws-all_20_23_24e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r101_fpn_gn_ws-all_2x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[20, 23]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/gn+ws/mask_rcnn_r101_fpn_gn_ws-all_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_gn_ws-all_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://jhu/resnet101_gn_ws', backbone=dict(depth=101)) 4 | -------------------------------------------------------------------------------- /configs/gn+ws/mask_rcnn_r50_fpn_gn_ws-all_20_23_24e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_gn_ws-all_2x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[20, 23]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/gn+ws/mask_rcnn_r50_fpn_gn_ws-all_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py' 2 | conv_cfg = dict(type='ConvWS') 3 | norm_cfg = dict(type='GN', num_groups=32, requires_grad=True) 4 | model = dict( 5 | pretrained='open-mmlab://jhu/resnet50_gn_ws', 6 | backbone=dict(conv_cfg=conv_cfg, norm_cfg=norm_cfg), 7 | neck=dict(conv_cfg=conv_cfg, norm_cfg=norm_cfg), 8 | roi_head=dict( 9 | bbox_head=dict( 10 | type='Shared4Conv1FCBBoxHead', 11 | conv_out_channels=256, 12 | conv_cfg=conv_cfg, 13 | norm_cfg=norm_cfg), 14 | mask_head=dict(conv_cfg=conv_cfg, norm_cfg=norm_cfg))) 15 | # learning policy 16 | lr_config = dict(step=[16, 22]) 17 | runner = dict(type='EpochBasedRunner', max_epochs=24) 18 | -------------------------------------------------------------------------------- /configs/gn+ws/mask_rcnn_x101_32x4d_fpn_gn_ws-all_20_23_24e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_x101_32x4d_fpn_gn_ws-all_2x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[20, 23]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/gn+ws/mask_rcnn_x101_32x4d_fpn_gn_ws-all_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_gn_ws-all_2x_coco.py' 2 | # model settings 3 | conv_cfg = dict(type='ConvWS') 4 | norm_cfg = dict(type='GN', num_groups=32, requires_grad=True) 5 | model = dict( 6 | pretrained='open-mmlab://jhu/resnext101_32x4d_gn_ws', 7 | backbone=dict( 8 | type='ResNeXt', 9 | depth=101, 10 | groups=32, 11 | base_width=4, 12 | num_stages=4, 13 | out_indices=(0, 1, 2, 3), 14 | frozen_stages=1, 15 | style='pytorch', 16 | conv_cfg=conv_cfg, 17 | norm_cfg=norm_cfg)) 18 | -------------------------------------------------------------------------------- /configs/gn+ws/mask_rcnn_x50_32x4d_fpn_gn_ws-all_20_23_24e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_x50_32x4d_fpn_gn_ws-all_2x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[20, 23]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/gn+ws/mask_rcnn_x50_32x4d_fpn_gn_ws-all_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_gn_ws-all_2x_coco.py' 2 | # model settings 3 | conv_cfg = dict(type='ConvWS') 4 | norm_cfg = dict(type='GN', num_groups=32, requires_grad=True) 5 | model = dict( 6 | pretrained='open-mmlab://jhu/resnext50_32x4d_gn_ws', 7 | backbone=dict( 8 | type='ResNeXt', 9 | depth=50, 10 | groups=32, 11 | base_width=4, 12 | num_stages=4, 13 | out_indices=(0, 1, 2, 3), 14 | frozen_stages=1, 15 | style='pytorch', 16 | conv_cfg=conv_cfg, 17 | norm_cfg=norm_cfg)) 18 | -------------------------------------------------------------------------------- /configs/gn/mask_rcnn_r101_fpn_gn-all_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_gn-all_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://detectron/resnet101_gn', backbone=dict(depth=101)) 4 | -------------------------------------------------------------------------------- /configs/gn/mask_rcnn_r101_fpn_gn-all_3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r101_fpn_gn-all_2x_coco.py' 2 | 3 | # learning policy 4 | lr_config = dict(step=[28, 34]) 5 | runner = dict(type='EpochBasedRunner', max_epochs=36) 6 | -------------------------------------------------------------------------------- /configs/gn/mask_rcnn_r50_fpn_gn-all_3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_gn-all_2x_coco.py' 2 | 3 | # learning policy 4 | lr_config = dict(step=[28, 34]) 5 | runner = dict(type='EpochBasedRunner', max_epochs=36) 6 | -------------------------------------------------------------------------------- /configs/gn/mask_rcnn_r50_fpn_gn-all_contrib_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py' 2 | norm_cfg = dict(type='GN', num_groups=32, requires_grad=True) 3 | model = dict( 4 | pretrained='open-mmlab://contrib/resnet50_gn', 5 | backbone=dict(norm_cfg=norm_cfg), 6 | neck=dict(norm_cfg=norm_cfg), 7 | roi_head=dict( 8 | bbox_head=dict( 9 | type='Shared4Conv1FCBBoxHead', 10 | conv_out_channels=256, 11 | norm_cfg=norm_cfg), 12 | mask_head=dict(norm_cfg=norm_cfg))) 13 | # learning policy 14 | lr_config = dict(step=[16, 22]) 15 | runner = dict(type='EpochBasedRunner', max_epochs=24) 16 | -------------------------------------------------------------------------------- /configs/gn/mask_rcnn_r50_fpn_gn-all_contrib_3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_gn-all_contrib_2x_coco.py' 2 | 3 | # learning policy 4 | lr_config = dict(step=[28, 34]) 5 | runner = dict(type='EpochBasedRunner', max_epochs=36) 6 | -------------------------------------------------------------------------------- /configs/grid_rcnn/grid_rcnn_r101_fpn_gn-head_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './grid_rcnn_r50_fpn_gn-head_2x_coco.py' 2 | 3 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 4 | -------------------------------------------------------------------------------- /configs/grid_rcnn/grid_rcnn_r50_fpn_gn-head_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = ['grid_rcnn_r50_fpn_gn-head_2x_coco.py'] 2 | # learning policy 3 | lr_config = dict( 4 | policy='step', 5 | warmup='linear', 6 | warmup_iters=500, 7 | warmup_ratio=0.001, 8 | step=[8, 11]) 9 | checkpoint_config = dict(interval=1) 10 | # runtime settings 11 | runner = dict(type='EpochBasedRunner', max_epochs=12) 12 | -------------------------------------------------------------------------------- /configs/grid_rcnn/grid_rcnn_x101_32x4d_fpn_gn-head_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './grid_rcnn_r50_fpn_gn-head_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | style='pytorch')) 13 | # optimizer 14 | optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) 15 | optimizer_config = dict(grad_clip=None) 16 | # learning policy 17 | lr_config = dict( 18 | policy='step', 19 | warmup='linear', 20 | warmup_iters=3665, 21 | warmup_ratio=1.0 / 80, 22 | step=[17, 23]) 23 | runner = dict(type='EpochBasedRunner', max_epochs=25) 24 | -------------------------------------------------------------------------------- /configs/grid_rcnn/grid_rcnn_x101_64x4d_fpn_gn-head_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './grid_rcnn_x101_32x4d_fpn_gn-head_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | style='pytorch')) 13 | -------------------------------------------------------------------------------- /configs/groie/faster_rcnn_r50_fpn_groie_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | # model settings 3 | model = dict( 4 | roi_head=dict( 5 | bbox_roi_extractor=dict( 6 | type='GenericRoIExtractor', 7 | aggregation='sum', 8 | roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=2), 9 | out_channels=256, 10 | featmap_strides=[4, 8, 16, 32], 11 | pre_cfg=dict( 12 | type='ConvModule', 13 | in_channels=256, 14 | out_channels=256, 15 | kernel_size=5, 16 | padding=2, 17 | inplace=False, 18 | ), 19 | post_cfg=dict( 20 | type='GeneralizedAttention', 21 | in_channels=256, 22 | spatial_range=-1, 23 | num_heads=6, 24 | attention_type='0100', 25 | kv_stride=2)))) 26 | -------------------------------------------------------------------------------- /configs/guided_anchoring/ga_faster_r101_caffe_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ga_faster_r50_caffe_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://detectron2/resnet101_caffe', 4 | backbone=dict(depth=101)) 5 | -------------------------------------------------------------------------------- /configs/guided_anchoring/ga_faster_x101_32x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ga_faster_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/guided_anchoring/ga_faster_x101_64x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ga_faster_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/guided_anchoring/ga_retinanet_r101_caffe_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ga_retinanet_r50_caffe_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://detectron2/resnet101_caffe', 4 | backbone=dict(depth=101)) 5 | -------------------------------------------------------------------------------- /configs/guided_anchoring/ga_retinanet_x101_32x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ga_retinanet_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/guided_anchoring/ga_retinanet_x101_64x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ga_retinanet_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/guided_anchoring/ga_rpn_r101_caffe_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ga_rpn_r50_caffe_fpn_1x_coco.py' 2 | # model settings 3 | model = dict( 4 | pretrained='open-mmlab://detectron2/resnet101_caffe', 5 | backbone=dict(depth=101)) 6 | -------------------------------------------------------------------------------- /configs/guided_anchoring/ga_rpn_x101_32x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ga_rpn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/guided_anchoring/ga_rpn_x101_64x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ga_rpn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/hrnet/cascade_mask_rcnn_hrnetv2p_w18_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_mask_rcnn_hrnetv2p_w32_20e_coco.py' 2 | # model settings 3 | model = dict( 4 | pretrained='open-mmlab://msra/hrnetv2_w18', 5 | backbone=dict( 6 | extra=dict( 7 | stage2=dict(num_channels=(18, 36)), 8 | stage3=dict(num_channels=(18, 36, 72)), 9 | stage4=dict(num_channels=(18, 36, 72, 144)))), 10 | neck=dict(type='HRFPN', in_channels=[18, 36, 72, 144], out_channels=256)) 11 | -------------------------------------------------------------------------------- /configs/hrnet/cascade_mask_rcnn_hrnetv2p_w40_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_mask_rcnn_hrnetv2p_w32_20e_coco.py' 2 | # model settings 3 | model = dict( 4 | pretrained='open-mmlab://msra/hrnetv2_w40', 5 | backbone=dict( 6 | type='HRNet', 7 | extra=dict( 8 | stage2=dict(num_channels=(40, 80)), 9 | stage3=dict(num_channels=(40, 80, 160)), 10 | stage4=dict(num_channels=(40, 80, 160, 320)))), 11 | neck=dict(type='HRFPN', in_channels=[40, 80, 160, 320], out_channels=256)) 12 | -------------------------------------------------------------------------------- /configs/hrnet/cascade_rcnn_hrnetv2p_w18_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_rcnn_hrnetv2p_w32_20e_coco.py' 2 | # model settings 3 | model = dict( 4 | pretrained='open-mmlab://msra/hrnetv2_w18', 5 | backbone=dict( 6 | extra=dict( 7 | stage2=dict(num_channels=(18, 36)), 8 | stage3=dict(num_channels=(18, 36, 72)), 9 | stage4=dict(num_channels=(18, 36, 72, 144)))), 10 | neck=dict(type='HRFPN', in_channels=[18, 36, 72, 144], out_channels=256)) 11 | -------------------------------------------------------------------------------- /configs/hrnet/cascade_rcnn_hrnetv2p_w40_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_rcnn_hrnetv2p_w32_20e_coco.py' 2 | # model settings 3 | model = dict( 4 | pretrained='open-mmlab://msra/hrnetv2_w40', 5 | backbone=dict( 6 | type='HRNet', 7 | extra=dict( 8 | stage2=dict(num_channels=(40, 80)), 9 | stage3=dict(num_channels=(40, 80, 160)), 10 | stage4=dict(num_channels=(40, 80, 160, 320)))), 11 | neck=dict(type='HRFPN', in_channels=[40, 80, 160, 320], out_channels=256)) 12 | -------------------------------------------------------------------------------- /configs/hrnet/faster_rcnn_hrnetv2p_w18_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_hrnetv2p_w32_1x_coco.py' 2 | # model settings 3 | model = dict( 4 | pretrained='open-mmlab://msra/hrnetv2_w18', 5 | backbone=dict( 6 | extra=dict( 7 | stage2=dict(num_channels=(18, 36)), 8 | stage3=dict(num_channels=(18, 36, 72)), 9 | stage4=dict(num_channels=(18, 36, 72, 144)))), 10 | neck=dict(type='HRFPN', in_channels=[18, 36, 72, 144], out_channels=256)) 11 | -------------------------------------------------------------------------------- /configs/hrnet/faster_rcnn_hrnetv2p_w18_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_hrnetv2p_w18_1x_coco.py' 2 | 3 | # learning policy 4 | lr_config = dict(step=[16, 22]) 5 | runner = dict(type='EpochBasedRunner', max_epochs=24) 6 | -------------------------------------------------------------------------------- /configs/hrnet/faster_rcnn_hrnetv2p_w32_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_hrnetv2p_w32_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 22]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/hrnet/faster_rcnn_hrnetv2p_w40_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_hrnetv2p_w32_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://msra/hrnetv2_w40', 4 | backbone=dict( 5 | type='HRNet', 6 | extra=dict( 7 | stage2=dict(num_channels=(40, 80)), 8 | stage3=dict(num_channels=(40, 80, 160)), 9 | stage4=dict(num_channels=(40, 80, 160, 320)))), 10 | neck=dict(type='HRFPN', in_channels=[40, 80, 160, 320], out_channels=256)) 11 | -------------------------------------------------------------------------------- /configs/hrnet/faster_rcnn_hrnetv2p_w40_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_hrnetv2p_w40_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 22]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/hrnet/fcos_hrnetv2p_w18_gn-head_4x4_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fcos_hrnetv2p_w32_gn-head_4x4_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://msra/hrnetv2_w18', 4 | backbone=dict( 5 | extra=dict( 6 | stage2=dict(num_channels=(18, 36)), 7 | stage3=dict(num_channels=(18, 36, 72)), 8 | stage4=dict(num_channels=(18, 36, 72, 144)))), 9 | neck=dict(type='HRFPN', in_channels=[18, 36, 72, 144], out_channels=256)) 10 | -------------------------------------------------------------------------------- /configs/hrnet/fcos_hrnetv2p_w18_gn-head_4x4_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fcos_hrnetv2p_w18_gn-head_4x4_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 22]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/hrnet/fcos_hrnetv2p_w18_gn-head_mstrain_640-800_4x4_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fcos_hrnetv2p_w32_gn-head_mstrain_640-800_4x4_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://msra/hrnetv2_w18', 4 | backbone=dict( 5 | extra=dict( 6 | stage2=dict(num_channels=(18, 36)), 7 | stage3=dict(num_channels=(18, 36, 72)), 8 | stage4=dict(num_channels=(18, 36, 72, 144)))), 9 | neck=dict(type='HRFPN', in_channels=[18, 36, 72, 144], out_channels=256)) 10 | -------------------------------------------------------------------------------- /configs/hrnet/fcos_hrnetv2p_w32_gn-head_4x4_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fcos_hrnetv2p_w32_gn-head_4x4_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 22]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/hrnet/fcos_hrnetv2p_w40_gn-head_mstrain_640-800_4x4_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './fcos_hrnetv2p_w32_gn-head_mstrain_640-800_4x4_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://msra/hrnetv2_w40', 4 | backbone=dict( 5 | type='HRNet', 6 | extra=dict( 7 | stage2=dict(num_channels=(40, 80)), 8 | stage3=dict(num_channels=(40, 80, 160)), 9 | stage4=dict(num_channels=(40, 80, 160, 320)))), 10 | neck=dict(type='HRFPN', in_channels=[40, 80, 160, 320], out_channels=256)) 11 | -------------------------------------------------------------------------------- /configs/hrnet/htc_hrnetv2p_w18_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './htc_hrnetv2p_w32_20e_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://msra/hrnetv2_w18', 4 | backbone=dict( 5 | extra=dict( 6 | stage2=dict(num_channels=(18, 36)), 7 | stage3=dict(num_channels=(18, 36, 72)), 8 | stage4=dict(num_channels=(18, 36, 72, 144)))), 9 | neck=dict(type='HRFPN', in_channels=[18, 36, 72, 144], out_channels=256)) 10 | -------------------------------------------------------------------------------- /configs/hrnet/htc_hrnetv2p_w40_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './htc_hrnetv2p_w32_20e_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://msra/hrnetv2_w40', 4 | backbone=dict( 5 | type='HRNet', 6 | extra=dict( 7 | stage2=dict(num_channels=(40, 80)), 8 | stage3=dict(num_channels=(40, 80, 160)), 9 | stage4=dict(num_channels=(40, 80, 160, 320)))), 10 | neck=dict(type='HRFPN', in_channels=[40, 80, 160, 320], out_channels=256)) 11 | -------------------------------------------------------------------------------- /configs/hrnet/htc_hrnetv2p_w40_28e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './htc_hrnetv2p_w40_20e_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[24, 27]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=28) 5 | -------------------------------------------------------------------------------- /configs/hrnet/htc_x101_64x4d_fpn_16x1_28e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../htc/htc_x101_64x4d_fpn_16x1_20e_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[24, 27]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=28) 5 | -------------------------------------------------------------------------------- /configs/hrnet/mask_rcnn_hrnetv2p_w18_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_hrnetv2p_w32_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://msra/hrnetv2_w18', 4 | backbone=dict( 5 | extra=dict( 6 | stage2=dict(num_channels=(18, 36)), 7 | stage3=dict(num_channels=(18, 36, 72)), 8 | stage4=dict(num_channels=(18, 36, 72, 144)))), 9 | neck=dict(type='HRFPN', in_channels=[18, 36, 72, 144], out_channels=256)) 10 | -------------------------------------------------------------------------------- /configs/hrnet/mask_rcnn_hrnetv2p_w18_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_hrnetv2p_w18_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 22]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/hrnet/mask_rcnn_hrnetv2p_w32_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_hrnetv2p_w32_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 22]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/hrnet/mask_rcnn_hrnetv2p_w40_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_hrnetv2p_w18_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://msra/hrnetv2_w40', 4 | backbone=dict( 5 | type='HRNet', 6 | extra=dict( 7 | stage2=dict(num_channels=(40, 80)), 8 | stage3=dict(num_channels=(40, 80, 160)), 9 | stage4=dict(num_channels=(40, 80, 160, 320)))), 10 | neck=dict(type='HRFPN', in_channels=[40, 80, 160, 320], out_channels=256)) 11 | -------------------------------------------------------------------------------- /configs/hrnet/mask_rcnn_hrnetv2p_w40_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_hrnetv2p_w40_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 22]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/htc/htc_r101_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './htc_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | # learning policy 4 | lr_config = dict(step=[16, 19]) 5 | runner = dict(type='EpochBasedRunner', max_epochs=20) 6 | -------------------------------------------------------------------------------- /configs/htc/htc_r50_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './htc_r50_fpn_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 19]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=20) 5 | -------------------------------------------------------------------------------- /configs/htc/htc_x101_32x4d_fpn_16x1_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './htc_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | norm_eval=True, 14 | style='pytorch')) 15 | data = dict(samples_per_gpu=1, workers_per_gpu=1) 16 | # learning policy 17 | lr_config = dict(step=[16, 19]) 18 | runner = dict(type='EpochBasedRunner', max_epochs=20) 19 | -------------------------------------------------------------------------------- /configs/htc/htc_x101_64x4d_fpn_16x1_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './htc_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | norm_eval=True, 14 | style='pytorch')) 15 | data = dict(samples_per_gpu=1, workers_per_gpu=1) 16 | # learning policy 17 | lr_config = dict(step=[16, 19]) 18 | runner = dict(type='EpochBasedRunner', max_epochs=20) 19 | -------------------------------------------------------------------------------- /configs/instaboost/cascade_mask_rcnn_r101_fpn_instaboost_4x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_mask_rcnn_r50_fpn_instaboost_4x_coco.py' 2 | 3 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 4 | -------------------------------------------------------------------------------- /configs/instaboost/cascade_mask_rcnn_x101_64x4d_fpn_instaboost_4x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_mask_rcnn_r50_fpn_instaboost_4x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/instaboost/mask_rcnn_r101_fpn_instaboost_4x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_instaboost_4x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/instaboost/mask_rcnn_x101_64x4d_fpn_instaboost_4x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_instaboost_4x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/ld/ld_r34_gflv1_r101_fpn_coco_1x.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./ld_r18_gflv1_r101_fpn_coco_1x.py'] 2 | model = dict( 3 | pretrained='torchvision://resnet34', 4 | backbone=dict( 5 | type='ResNet', 6 | depth=34, 7 | num_stages=4, 8 | out_indices=(0, 1, 2, 3), 9 | frozen_stages=1, 10 | norm_cfg=dict(type='BN', requires_grad=True), 11 | norm_eval=True, 12 | style='pytorch'), 13 | neck=dict( 14 | type='FPN', 15 | in_channels=[64, 128, 256, 512], 16 | out_channels=256, 17 | start_level=1, 18 | add_extra_convs='on_output', 19 | num_outs=5)) 20 | -------------------------------------------------------------------------------- /configs/ld/ld_r50_gflv1_r101_fpn_coco_1x.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./ld_r18_gflv1_r101_fpn_coco_1x.py'] 2 | model = dict( 3 | pretrained='torchvision://resnet50', 4 | backbone=dict( 5 | type='ResNet', 6 | depth=50, 7 | num_stages=4, 8 | out_indices=(0, 1, 2, 3), 9 | frozen_stages=1, 10 | norm_cfg=dict(type='BN', requires_grad=True), 11 | norm_eval=True, 12 | style='pytorch'), 13 | neck=dict( 14 | type='FPN', 15 | in_channels=[256, 512, 1024, 2048], 16 | out_channels=256, 17 | start_level=1, 18 | add_extra_convs='on_output', 19 | num_outs=5)) 20 | -------------------------------------------------------------------------------- /configs/legacy_1.x/retinanet_r50_fpn_1x_coco_v1.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/retinanet_r50_fpn.py', 3 | '../_base_/datasets/coco_detection.py', 4 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 5 | ] 6 | model = dict( 7 | bbox_head=dict( 8 | type='RetinaHead', 9 | anchor_generator=dict( 10 | type='LegacyAnchorGenerator', 11 | center_offset=0.5, 12 | octave_base_scale=4, 13 | scales_per_octave=3, 14 | ratios=[0.5, 1.0, 2.0], 15 | strides=[8, 16, 32, 64, 128]), 16 | bbox_coder=dict(type='LegacyDeltaXYWHBBoxCoder'), 17 | loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0))) 18 | -------------------------------------------------------------------------------- /configs/libra_rcnn/libra_faster_rcnn_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './libra_faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/libra_rcnn/libra_faster_rcnn_x101_64x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './libra_faster_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/libra_rcnn/libra_retinanet_r50_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../retinanet/retinanet_r50_fpn_1x_coco.py' 2 | # model settings 3 | model = dict( 4 | neck=[ 5 | dict( 6 | type='FPN', 7 | in_channels=[256, 512, 1024, 2048], 8 | out_channels=256, 9 | start_level=1, 10 | add_extra_convs='on_input', 11 | num_outs=5), 12 | dict( 13 | type='BFP', 14 | in_channels=256, 15 | num_levels=5, 16 | refine_level=1, 17 | refine_type='non_local') 18 | ], 19 | bbox_head=dict( 20 | loss_bbox=dict( 21 | _delete_=True, 22 | type='BalancedL1Loss', 23 | alpha=0.5, 24 | gamma=1.5, 25 | beta=0.11, 26 | loss_weight=1.0))) 27 | -------------------------------------------------------------------------------- /configs/lvis/mask_rcnn_r101_fpn_sample1e-3_mstrain_1x_lvis_v1.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_sample1e-3_mstrain_1x_lvis_v1.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/lvis/mask_rcnn_r101_fpn_sample1e-3_mstrain_2x_lvis_v0.5.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_sample1e-3_mstrain_2x_lvis_v0.5.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/lvis/mask_rcnn_x101_32x4d_fpn_sample1e-3_mstrain_1x_lvis_v1.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_sample1e-3_mstrain_1x_lvis_v1.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/lvis/mask_rcnn_x101_32x4d_fpn_sample1e-3_mstrain_2x_lvis_v0.5.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_sample1e-3_mstrain_2x_lvis_v0.5.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/lvis/mask_rcnn_x101_64x4d_fpn_sample1e-3_mstrain_1x_lvis_v1.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_sample1e-3_mstrain_1x_lvis_v1.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/lvis/mask_rcnn_x101_64x4d_fpn_sample1e-3_mstrain_2x_lvis_v0.5.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_sample1e-3_mstrain_2x_lvis_v0.5.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/mask_rcnn/mask_rcnn_r101_caffe_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_caffe_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://detectron2/resnet101_caffe', 4 | backbone=dict(depth=101)) 5 | -------------------------------------------------------------------------------- /configs/mask_rcnn/mask_rcnn_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/mask_rcnn/mask_rcnn_r101_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_fpn_2x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_caffe_fpn_mstrain-poly_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 23]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r50_caffe_fpn_mstrain-poly_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[28, 34]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=36) 5 | -------------------------------------------------------------------------------- /configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/mask_rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_instance.py', 4 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /configs/mask_rcnn/mask_rcnn_r50_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/mask_rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_instance.py', 4 | '../_base_/schedules/schedule_2x.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /configs/mask_rcnn/mask_rcnn_r50_fpn_poly_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/mask_rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_instance.py', 4 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 5 | ] 6 | 7 | img_norm_cfg = dict( 8 | mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) 9 | train_pipeline = [ 10 | dict(type='LoadImageFromFile'), 11 | dict( 12 | type='LoadAnnotations', 13 | with_bbox=True, 14 | with_mask=True, 15 | poly2mask=False), 16 | dict(type='Resize', img_scale=(1333, 800), keep_ratio=True), 17 | dict(type='RandomFlip', flip_ratio=0.5), 18 | dict(type='Normalize', **img_norm_cfg), 19 | dict(type='Pad', size_divisor=32), 20 | dict(type='DefaultFormatBundle'), 21 | dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']), 22 | ] 23 | data = dict(train=dict(pipeline=train_pipeline)) 24 | -------------------------------------------------------------------------------- /configs/mask_rcnn/mask_rcnn_x101_32x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r101_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/mask_rcnn/mask_rcnn_x101_32x4d_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_r101_fpn_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/mask_rcnn/mask_rcnn_x101_64x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_x101_32x4d_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/mask_rcnn/mask_rcnn_x101_64x4d_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_x101_32x4d_fpn_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/ms_rcnn/ms_rcnn_r101_caffe_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ms_rcnn_r50_caffe_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://detectron2/resnet101_caffe', 4 | backbone=dict(depth=101)) 5 | -------------------------------------------------------------------------------- /configs/ms_rcnn/ms_rcnn_r101_caffe_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ms_rcnn_r101_caffe_fpn_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 22]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/ms_rcnn/ms_rcnn_r50_caffe_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r50_caffe_fpn_1x_coco.py' 2 | model = dict( 3 | type='MaskScoringRCNN', 4 | roi_head=dict( 5 | type='MaskScoringRoIHead', 6 | mask_iou_head=dict( 7 | type='MaskIoUHead', 8 | num_convs=4, 9 | num_fcs=2, 10 | roi_feat_size=14, 11 | in_channels=256, 12 | conv_out_channels=256, 13 | fc_out_channels=1024, 14 | num_classes=80)), 15 | # model training and testing settings 16 | train_cfg=dict(rcnn=dict(mask_thr_binary=0.5))) 17 | -------------------------------------------------------------------------------- /configs/ms_rcnn/ms_rcnn_r50_caffe_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ms_rcnn_r50_caffe_fpn_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 22]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/ms_rcnn/ms_rcnn_r50_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | type='MaskScoringRCNN', 4 | roi_head=dict( 5 | type='MaskScoringRoIHead', 6 | mask_iou_head=dict( 7 | type='MaskIoUHead', 8 | num_convs=4, 9 | num_fcs=2, 10 | roi_feat_size=14, 11 | in_channels=256, 12 | conv_out_channels=256, 13 | fc_out_channels=1024, 14 | num_classes=80)), 15 | # model training and testing settings 16 | train_cfg=dict(rcnn=dict(mask_thr_binary=0.5))) 17 | -------------------------------------------------------------------------------- /configs/ms_rcnn/ms_rcnn_x101_32x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ms_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/ms_rcnn/ms_rcnn_x101_64x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ms_rcnn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/ms_rcnn/ms_rcnn_x101_64x4d_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './ms_rcnn_x101_64x4d_fpn_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 22]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/paa/paa_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './paa_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/paa/paa_r101_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './paa_r101_fpn_1x_coco.py' 2 | lr_config = dict(step=[16, 22]) 3 | runner = dict(type='EpochBasedRunner', max_epochs=24) 4 | -------------------------------------------------------------------------------- /configs/paa/paa_r101_fpn_mstrain_3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './paa_r50_fpn_mstrain_3x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/paa/paa_r50_fpn_1.5x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './paa_r50_fpn_1x_coco.py' 2 | lr_config = dict(step=[12, 16]) 3 | runner = dict(type='EpochBasedRunner', max_epochs=18) 4 | -------------------------------------------------------------------------------- /configs/paa/paa_r50_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './paa_r50_fpn_1x_coco.py' 2 | lr_config = dict(step=[16, 22]) 3 | runner = dict(type='EpochBasedRunner', max_epochs=24) 4 | -------------------------------------------------------------------------------- /configs/paa/paa_r50_fpn_mstrain_3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './paa_r50_fpn_1x_coco.py' 2 | img_norm_cfg = dict( 3 | mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) 4 | train_pipeline = [ 5 | dict(type='LoadImageFromFile'), 6 | dict(type='LoadAnnotations', with_bbox=True), 7 | dict( 8 | type='Resize', 9 | img_scale=[(1333, 640), (1333, 800)], 10 | multiscale_mode='range', 11 | keep_ratio=True), 12 | dict(type='RandomFlip', flip_ratio=0.5), 13 | dict(type='Normalize', **img_norm_cfg), 14 | dict(type='Pad', size_divisor=32), 15 | dict(type='DefaultFormatBundle'), 16 | dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']), 17 | ] 18 | data = dict(train=dict(pipeline=train_pipeline)) 19 | lr_config = dict(step=[28, 34]) 20 | runner = dict(type='EpochBasedRunner', max_epochs=36) 21 | -------------------------------------------------------------------------------- /configs/pafpn/faster_rcnn_r50_pafpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py' 2 | 3 | model = dict( 4 | neck=dict( 5 | type='PAFPN', 6 | in_channels=[256, 512, 1024, 2048], 7 | out_channels=256, 8 | num_outs=5)) 9 | -------------------------------------------------------------------------------- /configs/pascal_voc/faster_rcnn_r50_fpn_1x_voc0712.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/faster_rcnn_r50_fpn.py', '../_base_/datasets/voc0712.py', 3 | '../_base_/default_runtime.py' 4 | ] 5 | model = dict(roi_head=dict(bbox_head=dict(num_classes=20))) 6 | # optimizer 7 | optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001) 8 | optimizer_config = dict(grad_clip=None) 9 | # learning policy 10 | # actual epoch = 3 * 3 = 9 11 | lr_config = dict(policy='step', step=[3]) 12 | # runtime settings 13 | runner = dict( 14 | type='EpochBasedRunner', max_epochs=4) # actual epoch = 4 * 3 = 12 15 | -------------------------------------------------------------------------------- /configs/pascal_voc/retinanet_r50_fpn_1x_voc0712.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/retinanet_r50_fpn.py', '../_base_/datasets/voc0712.py', 3 | '../_base_/default_runtime.py' 4 | ] 5 | model = dict(bbox_head=dict(num_classes=20)) 6 | # optimizer 7 | optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001) 8 | optimizer_config = dict(grad_clip=None) 9 | # learning policy 10 | # actual epoch = 3 * 3 = 9 11 | lr_config = dict(policy='step', step=[3]) 12 | # runtime settings 13 | runner = dict( 14 | type='EpochBasedRunner', max_epochs=4) # actual epoch = 4 * 3 = 12 15 | -------------------------------------------------------------------------------- /configs/pisa/pisa_retinanet_r50_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../retinanet/retinanet_r50_fpn_1x_coco.py' 2 | 3 | model = dict( 4 | bbox_head=dict( 5 | type='PISARetinaHead', 6 | loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)), 7 | train_cfg=dict(isr=dict(k=2., bias=0.), carl=dict(k=1., bias=0.2))) 8 | -------------------------------------------------------------------------------- /configs/pisa/pisa_retinanet_x101_32x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../retinanet/retinanet_x101_32x4d_fpn_1x_coco.py' 2 | 3 | model = dict( 4 | bbox_head=dict( 5 | type='PISARetinaHead', 6 | loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)), 7 | train_cfg=dict(isr=dict(k=2., bias=0.), carl=dict(k=1., bias=0.2))) 8 | -------------------------------------------------------------------------------- /configs/pisa/pisa_ssd300_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../ssd/ssd300_coco.py' 2 | 3 | model = dict( 4 | bbox_head=dict(type='PISASSDHead'), 5 | train_cfg=dict(isr=dict(k=2., bias=0.), carl=dict(k=1., bias=0.2))) 6 | 7 | optimizer_config = dict( 8 | _delete_=True, grad_clip=dict(max_norm=35, norm_type=2)) 9 | -------------------------------------------------------------------------------- /configs/pisa/pisa_ssd512_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../ssd/ssd512_coco.py' 2 | 3 | model = dict( 4 | bbox_head=dict(type='PISASSDHead'), 5 | train_cfg=dict(isr=dict(k=2., bias=0.), carl=dict(k=1., bias=0.2))) 6 | 7 | optimizer_config = dict( 8 | _delete_=True, grad_clip=dict(max_norm=35, norm_type=2)) 9 | -------------------------------------------------------------------------------- /configs/point_rend/point_rend_r50_caffe_fpn_mstrain_3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './point_rend_r50_caffe_fpn_mstrain_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[28, 34]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=36) 5 | -------------------------------------------------------------------------------- /configs/regnet/faster_rcnn_regnetx-3.2GF_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_regnetx-3.2GF_fpn_1x_coco.py' 2 | lr_config = dict(step=[16, 22]) 3 | runner = dict(type='EpochBasedRunner', max_epochs=24) 4 | -------------------------------------------------------------------------------- /configs/regnet/mask_rcnn_regnetx-12GF_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_regnetx-3.2GF_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://regnetx_12gf', 4 | backbone=dict( 5 | type='RegNet', 6 | arch='regnetx_12gf', 7 | out_indices=(0, 1, 2, 3), 8 | frozen_stages=1, 9 | norm_cfg=dict(type='BN', requires_grad=True), 10 | norm_eval=True, 11 | style='pytorch'), 12 | neck=dict( 13 | type='FPN', 14 | in_channels=[224, 448, 896, 2240], 15 | out_channels=256, 16 | num_outs=5)) 17 | -------------------------------------------------------------------------------- /configs/regnet/mask_rcnn_regnetx-3.2GF_fpn_mdconv_c3-c5_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = 'mask_rcnn_regnetx-3.2GF_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://regnetx_3.2gf', 4 | backbone=dict( 5 | dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False), 6 | stage_with_dcn=(False, True, True, True))) 7 | -------------------------------------------------------------------------------- /configs/regnet/mask_rcnn_regnetx-4GF_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_regnetx-3.2GF_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://regnetx_4.0gf', 4 | backbone=dict( 5 | type='RegNet', 6 | arch='regnetx_4.0gf', 7 | out_indices=(0, 1, 2, 3), 8 | frozen_stages=1, 9 | norm_cfg=dict(type='BN', requires_grad=True), 10 | norm_eval=True, 11 | style='pytorch'), 12 | neck=dict( 13 | type='FPN', 14 | in_channels=[80, 240, 560, 1360], 15 | out_channels=256, 16 | num_outs=5)) 17 | -------------------------------------------------------------------------------- /configs/regnet/mask_rcnn_regnetx-6.4GF_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_regnetx-3.2GF_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://regnetx_6.4gf', 4 | backbone=dict( 5 | type='RegNet', 6 | arch='regnetx_6.4gf', 7 | out_indices=(0, 1, 2, 3), 8 | frozen_stages=1, 9 | norm_cfg=dict(type='BN', requires_grad=True), 10 | norm_eval=True, 11 | style='pytorch'), 12 | neck=dict( 13 | type='FPN', 14 | in_channels=[168, 392, 784, 1624], 15 | out_channels=256, 16 | num_outs=5)) 17 | -------------------------------------------------------------------------------- /configs/regnet/mask_rcnn_regnetx-8GF_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_regnetx-3.2GF_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://regnetx_8.0gf', 4 | backbone=dict( 5 | type='RegNet', 6 | arch='regnetx_8.0gf', 7 | out_indices=(0, 1, 2, 3), 8 | frozen_stages=1, 9 | norm_cfg=dict(type='BN', requires_grad=True), 10 | norm_eval=True, 11 | style='pytorch'), 12 | neck=dict( 13 | type='FPN', 14 | in_channels=[80, 240, 720, 1920], 15 | out_channels=256, 16 | num_outs=5)) 17 | -------------------------------------------------------------------------------- /configs/regnet/retinanet_regnetx-1.6GF_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_regnetx-3.2GF_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://regnetx_1.6gf', 4 | backbone=dict( 5 | type='RegNet', 6 | arch='regnetx_1.6gf', 7 | out_indices=(0, 1, 2, 3), 8 | frozen_stages=1, 9 | norm_cfg=dict(type='BN', requires_grad=True), 10 | norm_eval=True, 11 | style='pytorch'), 12 | neck=dict( 13 | type='FPN', 14 | in_channels=[72, 168, 408, 912], 15 | out_channels=256, 16 | num_outs=5)) 17 | -------------------------------------------------------------------------------- /configs/regnet/retinanet_regnetx-800MF_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_regnetx-3.2GF_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://regnetx_800mf', 4 | backbone=dict( 5 | type='RegNet', 6 | arch='regnetx_800mf', 7 | out_indices=(0, 1, 2, 3), 8 | frozen_stages=1, 9 | norm_cfg=dict(type='BN', requires_grad=True), 10 | norm_eval=True, 11 | style='pytorch'), 12 | neck=dict( 13 | type='FPN', 14 | in_channels=[64, 128, 288, 672], 15 | out_channels=256, 16 | num_outs=5)) 17 | -------------------------------------------------------------------------------- /configs/reppoints/bbox_r50_grid_center_fpn_gn-neck+head_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './reppoints_moment_r50_fpn_gn-neck+head_1x_coco.py' 2 | model = dict(bbox_head=dict(transform_method='minmax', use_grid_points=True)) 3 | -------------------------------------------------------------------------------- /configs/reppoints/bbox_r50_grid_fpn_gn-neck+head_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './reppoints_moment_r50_fpn_gn-neck+head_1x_coco.py' 2 | model = dict( 3 | bbox_head=dict(transform_method='minmax', use_grid_points=True), 4 | # training and testing settings 5 | train_cfg=dict( 6 | init=dict( 7 | assigner=dict( 8 | _delete_=True, 9 | type='MaxIoUAssigner', 10 | pos_iou_thr=0.5, 11 | neg_iou_thr=0.4, 12 | min_pos_iou=0, 13 | ignore_iof_thr=-1)))) 14 | -------------------------------------------------------------------------------- /configs/reppoints/reppoints.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/configs/reppoints/reppoints.png -------------------------------------------------------------------------------- /configs/reppoints/reppoints_minmax_r50_fpn_gn-neck+head_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './reppoints_moment_r50_fpn_gn-neck+head_1x_coco.py' 2 | model = dict(bbox_head=dict(transform_method='minmax')) 3 | -------------------------------------------------------------------------------- /configs/reppoints/reppoints_moment_r101_fpn_dconv_c3-c5_gn-neck+head_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './reppoints_moment_r50_fpn_gn-neck+head_2x_coco.py' 2 | model = dict( 3 | pretrained='torchvision://resnet101', 4 | backbone=dict( 5 | depth=101, 6 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 7 | stage_with_dcn=(False, True, True, True))) 8 | -------------------------------------------------------------------------------- /configs/reppoints/reppoints_moment_r101_fpn_gn-neck+head_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './reppoints_moment_r50_fpn_gn-neck+head_2x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/reppoints/reppoints_moment_r50_fpn_gn-neck+head_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './reppoints_moment_r50_fpn_1x_coco.py' 2 | norm_cfg = dict(type='GN', num_groups=32, requires_grad=True) 3 | model = dict(neck=dict(norm_cfg=norm_cfg), bbox_head=dict(norm_cfg=norm_cfg)) 4 | optimizer = dict(lr=0.01) 5 | -------------------------------------------------------------------------------- /configs/reppoints/reppoints_moment_r50_fpn_gn-neck+head_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './reppoints_moment_r50_fpn_gn-neck+head_1x_coco.py' 2 | lr_config = dict(step=[16, 22]) 3 | runner = dict(type='EpochBasedRunner', max_epochs=24) 4 | -------------------------------------------------------------------------------- /configs/reppoints/reppoints_moment_x101_fpn_dconv_c3-c5_gn-neck+head_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './reppoints_moment_r50_fpn_gn-neck+head_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch', 14 | dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False), 15 | stage_with_dcn=(False, True, True, True))) 16 | -------------------------------------------------------------------------------- /configs/reppoints/reppoints_partial_minmax_r50_fpn_gn-neck+head_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './reppoints_moment_r50_fpn_gn-neck+head_1x_coco.py' 2 | model = dict(bbox_head=dict(transform_method='partial_minmax')) 3 | -------------------------------------------------------------------------------- /configs/res2net/cascade_mask_rcnn_r2_101_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../cascade_rcnn/cascade_mask_rcnn_r50_fpn_20e_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://res2net101_v1d_26w_4s', 4 | backbone=dict(type='Res2Net', depth=101, scales=4, base_width=26)) 5 | -------------------------------------------------------------------------------- /configs/res2net/cascade_rcnn_r2_101_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../cascade_rcnn/cascade_rcnn_r50_fpn_20e_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://res2net101_v1d_26w_4s', 4 | backbone=dict(type='Res2Net', depth=101, scales=4, base_width=26)) 5 | -------------------------------------------------------------------------------- /configs/res2net/faster_rcnn_r2_101_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../faster_rcnn/faster_rcnn_r50_fpn_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://res2net101_v1d_26w_4s', 4 | backbone=dict(type='Res2Net', depth=101, scales=4, base_width=26)) 5 | -------------------------------------------------------------------------------- /configs/res2net/htc_r2_101_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../htc/htc_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://res2net101_v1d_26w_4s', 4 | backbone=dict(type='Res2Net', depth=101, scales=4, base_width=26)) 5 | # learning policy 6 | lr_config = dict(step=[16, 19]) 7 | runner = dict(type='EpochBasedRunner', max_epochs=20) 8 | -------------------------------------------------------------------------------- /configs/res2net/mask_rcnn_r2_101_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = '../mask_rcnn/mask_rcnn_r50_fpn_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://res2net101_v1d_26w_4s', 4 | backbone=dict(type='Res2Net', depth=101, scales=4, base_width=26)) 5 | -------------------------------------------------------------------------------- /configs/resnest/cascade_mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnest101', 4 | backbone=dict(stem_channels=128, depth=101)) 5 | -------------------------------------------------------------------------------- /configs/resnest/cascade_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnest101', 4 | backbone=dict(stem_channels=128, depth=101)) 5 | -------------------------------------------------------------------------------- /configs/resnest/faster_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './faster_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnest101', 4 | backbone=dict(stem_channels=128, depth=101)) 5 | -------------------------------------------------------------------------------- /configs/resnest/mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnest101', 4 | backbone=dict(stem_channels=128, depth=101)) 5 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_r101_caffe_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_r50_caffe_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://detectron2/resnet101_caffe', 4 | backbone=dict(depth=101)) 5 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_r101_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_r50_fpn_2x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_r50_caffe_fpn_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_r50_caffe_fpn_mstrain_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 23]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_r50_caffe_fpn_mstrain_3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_r50_caffe_fpn_mstrain_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[28, 34]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=36) 5 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_r50_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/retinanet_r50_fpn.py', 3 | '../_base_/datasets/coco_detection.py', 4 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 5 | ] 6 | # optimizer 7 | optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001) 8 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_r50_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_r50_fpn_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 22]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_x101_32x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_x101_32x4d_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_r50_fpn_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_x101_64x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/retinanet/retinanet_x101_64x4d_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './retinanet_r50_fpn_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/rpn/rpn_r101_caffe_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './rpn_r50_caffe_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://detectron2/resnet101_caffe', 4 | backbone=dict(depth=101)) 5 | -------------------------------------------------------------------------------- /configs/rpn/rpn_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './rpn_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/rpn/rpn_r101_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './rpn_r50_fpn_2x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/rpn/rpn_r50_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/rpn_r50_fpn.py', '../_base_/datasets/coco_detection.py', 3 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 4 | ] 5 | img_norm_cfg = dict( 6 | mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) 7 | train_pipeline = [ 8 | dict(type='LoadImageFromFile'), 9 | dict(type='LoadAnnotations', with_bbox=True, with_label=False), 10 | dict(type='Resize', img_scale=(1333, 800), keep_ratio=True), 11 | dict(type='RandomFlip', flip_ratio=0.5), 12 | dict(type='Normalize', **img_norm_cfg), 13 | dict(type='Pad', size_divisor=32), 14 | dict(type='DefaultFormatBundle'), 15 | dict(type='Collect', keys=['img', 'gt_bboxes']), 16 | ] 17 | data = dict(train=dict(pipeline=train_pipeline)) 18 | evaluation = dict(interval=1, metric='proposal_fast') 19 | -------------------------------------------------------------------------------- /configs/rpn/rpn_r50_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './rpn_r50_fpn_1x_coco.py' 2 | 3 | # learning policy 4 | lr_config = dict(step=[16, 22]) 5 | runner = dict(type='EpochBasedRunner', max_epochs=24) 6 | -------------------------------------------------------------------------------- /configs/rpn/rpn_x101_32x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './rpn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/rpn/rpn_x101_32x4d_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './rpn_r50_fpn_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/rpn/rpn_x101_64x4d_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './rpn_r50_fpn_1x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/rpn/rpn_x101_64x4d_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './rpn_r50_fpn_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | style='pytorch')) 14 | -------------------------------------------------------------------------------- /configs/scnet/scnet_r101_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './scnet_r50_fpn_20e_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/scnet/scnet_r50_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './scnet_r50_fpn_1x_coco.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 19]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=20) 5 | -------------------------------------------------------------------------------- /configs/scnet/scnet_x101_64x4d_fpn_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './scnet_r50_fpn_20e_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | norm_eval=True, 14 | style='pytorch')) 15 | -------------------------------------------------------------------------------- /configs/scnet/scnet_x101_64x4d_fpn_8x1_20e_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './scnet_x101_64x4d_fpn_20e_coco.py' 2 | data = dict(samples_per_gpu=1, workers_per_gpu=1) 3 | optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001) 4 | -------------------------------------------------------------------------------- /configs/scratch/faster_rcnn_r50_fpn_gn-all_scratch_6x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/faster_rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_detection.py', 4 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 5 | ] 6 | norm_cfg = dict(type='GN', num_groups=32, requires_grad=True) 7 | model = dict( 8 | pretrained=None, 9 | backbone=dict( 10 | frozen_stages=-1, zero_init_residual=False, norm_cfg=norm_cfg), 11 | neck=dict(norm_cfg=norm_cfg), 12 | roi_head=dict( 13 | bbox_head=dict( 14 | type='Shared4Conv1FCBBoxHead', 15 | conv_out_channels=256, 16 | norm_cfg=norm_cfg))) 17 | # optimizer 18 | optimizer = dict(paramwise_cfg=dict(norm_decay_mult=0)) 19 | optimizer_config = dict(_delete_=True, grad_clip=None) 20 | # learning policy 21 | lr_config = dict(warmup_ratio=0.1, step=[65, 71]) 22 | runner = dict(type='EpochBasedRunner', max_epochs=73) 23 | -------------------------------------------------------------------------------- /configs/scratch/mask_rcnn_r50_fpn_gn-all_scratch_6x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/mask_rcnn_r50_fpn.py', 3 | '../_base_/datasets/coco_instance.py', 4 | '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' 5 | ] 6 | norm_cfg = dict(type='GN', num_groups=32, requires_grad=True) 7 | model = dict( 8 | pretrained=None, 9 | backbone=dict( 10 | frozen_stages=-1, zero_init_residual=False, norm_cfg=norm_cfg), 11 | neck=dict(norm_cfg=norm_cfg), 12 | roi_head=dict( 13 | bbox_head=dict( 14 | type='Shared4Conv1FCBBoxHead', 15 | conv_out_channels=256, 16 | norm_cfg=norm_cfg), 17 | mask_head=dict(norm_cfg=norm_cfg))) 18 | # optimizer 19 | optimizer = dict(paramwise_cfg=dict(norm_decay_mult=0)) 20 | optimizer_config = dict(_delete_=True, grad_clip=None) 21 | # learning policy 22 | lr_config = dict(warmup_ratio=0.1, step=[65, 71]) 23 | runner = dict(type='EpochBasedRunner', max_epochs=73) 24 | -------------------------------------------------------------------------------- /configs/sparse_rcnn/sparse_rcnn_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './sparse_rcnn_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco.py' 2 | 3 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 4 | -------------------------------------------------------------------------------- /configs/sparse_rcnn/sparse_rcnn_r101_fpn_mstrain_480-800_3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './sparse_rcnn_r50_fpn_mstrain_480-800_3x_coco.py' 2 | 3 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 4 | -------------------------------------------------------------------------------- /configs/sparse_rcnn/sparse_rcnn_r50_fpn_mstrain_480-800_3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './sparse_rcnn_r50_fpn_1x_coco.py' 2 | 3 | img_norm_cfg = dict( 4 | mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) 5 | min_values = (480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800) 6 | train_pipeline = [ 7 | dict(type='LoadImageFromFile'), 8 | dict(type='LoadAnnotations', with_bbox=True), 9 | dict( 10 | type='Resize', 11 | img_scale=[(1333, value) for value in min_values], 12 | multiscale_mode='value', 13 | keep_ratio=True), 14 | dict(type='RandomFlip', flip_ratio=0.5), 15 | dict(type='Normalize', **img_norm_cfg), 16 | dict(type='Pad', size_divisor=32), 17 | dict(type='DefaultFormatBundle'), 18 | dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) 19 | ] 20 | 21 | data = dict(train=dict(pipeline=train_pipeline)) 22 | lr_config = dict(policy='step', step=[27, 33]) 23 | runner = dict(type='EpochBasedRunner', max_epochs=36) 24 | -------------------------------------------------------------------------------- /configs/tridentnet/tridentnet_r50_caffe_mstrain_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = 'tridentnet_r50_caffe_1x_coco.py' 2 | 3 | # use caffe img_norm 4 | img_norm_cfg = dict( 5 | mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False) 6 | train_pipeline = [ 7 | dict(type='LoadImageFromFile'), 8 | dict(type='LoadAnnotations', with_bbox=True), 9 | dict( 10 | type='Resize', 11 | img_scale=[(1333, 640), (1333, 672), (1333, 704), (1333, 736), 12 | (1333, 768), (1333, 800)], 13 | multiscale_mode='value', 14 | keep_ratio=True), 15 | dict(type='RandomFlip', flip_ratio=0.5), 16 | dict(type='Normalize', **img_norm_cfg), 17 | dict(type='Pad', size_divisor=32), 18 | dict(type='DefaultFormatBundle'), 19 | dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) 20 | ] 21 | 22 | data = dict(train=dict(pipeline=train_pipeline)) 23 | -------------------------------------------------------------------------------- /configs/tridentnet/tridentnet_r50_caffe_mstrain_3x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = 'tridentnet_r50_caffe_mstrain_1x_coco.py' 2 | 3 | lr_config = dict(step=[28, 34]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=36) 5 | -------------------------------------------------------------------------------- /configs/vfnet/vfnet_r101_fpn_1x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './vfnet_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/vfnet/vfnet_r101_fpn_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './vfnet_r50_fpn_1x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | lr_config = dict(step=[16, 22]) 4 | runner = dict(type='EpochBasedRunner', max_epochs=24) 5 | -------------------------------------------------------------------------------- /configs/vfnet/vfnet_r101_fpn_mdconv_c3-c5_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './vfnet_r50_fpn_mdconv_c3-c5_mstrain_2x_coco.py' 2 | model = dict( 3 | pretrained='torchvision://resnet101', 4 | backbone=dict( 5 | type='ResNet', 6 | depth=101, 7 | num_stages=4, 8 | out_indices=(0, 1, 2, 3), 9 | frozen_stages=1, 10 | norm_cfg=dict(type='BN', requires_grad=True), 11 | norm_eval=True, 12 | style='pytorch', 13 | dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False), 14 | stage_with_dcn=(False, True, True, True))) 15 | -------------------------------------------------------------------------------- /configs/vfnet/vfnet_r101_fpn_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './vfnet_r50_fpn_mstrain_2x_coco.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/vfnet/vfnet_r2_101_fpn_mdconv_c3-c5_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './vfnet_r50_fpn_mdconv_c3-c5_mstrain_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://res2net101_v1d_26w_4s', 4 | backbone=dict( 5 | type='Res2Net', 6 | depth=101, 7 | scales=4, 8 | base_width=26, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | norm_eval=True, 14 | style='pytorch', 15 | dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False), 16 | stage_with_dcn=(False, True, True, True))) 17 | -------------------------------------------------------------------------------- /configs/vfnet/vfnet_r2_101_fpn_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './vfnet_r50_fpn_mstrain_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://res2net101_v1d_26w_4s', 4 | backbone=dict( 5 | type='Res2Net', 6 | depth=101, 7 | scales=4, 8 | base_width=26, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | norm_eval=True, 14 | style='pytorch')) 15 | -------------------------------------------------------------------------------- /configs/vfnet/vfnet_r50_fpn_mdconv_c3-c5_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './vfnet_r50_fpn_mstrain_2x_coco.py' 2 | model = dict( 3 | backbone=dict( 4 | dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False), 5 | stage_with_dcn=(False, True, True, True)), 6 | bbox_head=dict(dcn_on_last_conv=True)) 7 | -------------------------------------------------------------------------------- /configs/vfnet/vfnet_x101_32x4d_fpn_mdconv_c3-c5_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './vfnet_r50_fpn_mdconv_c3-c5_mstrain_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | norm_eval=True, 14 | style='pytorch', 15 | dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False), 16 | stage_with_dcn=(False, True, True, True))) 17 | -------------------------------------------------------------------------------- /configs/vfnet/vfnet_x101_32x4d_fpn_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './vfnet_r50_fpn_mstrain_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_32x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=32, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | norm_eval=True, 14 | style='pytorch')) 15 | -------------------------------------------------------------------------------- /configs/vfnet/vfnet_x101_64x4d_fpn_mdconv_c3-c5_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './vfnet_r50_fpn_mdconv_c3-c5_mstrain_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | norm_eval=True, 14 | style='pytorch', 15 | dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False), 16 | stage_with_dcn=(False, True, True, True))) 17 | -------------------------------------------------------------------------------- /configs/vfnet/vfnet_x101_64x4d_fpn_mstrain_2x_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './vfnet_r50_fpn_mstrain_2x_coco.py' 2 | model = dict( 3 | pretrained='open-mmlab://resnext101_64x4d', 4 | backbone=dict( 5 | type='ResNeXt', 6 | depth=101, 7 | groups=64, 8 | base_width=4, 9 | num_stages=4, 10 | out_indices=(0, 1, 2, 3), 11 | frozen_stages=1, 12 | norm_cfg=dict(type='BN', requires_grad=True), 13 | norm_eval=True, 14 | style='pytorch')) 15 | -------------------------------------------------------------------------------- /configs/wider_face/ssd300_wider_face.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/ssd300.py', '../_base_/datasets/wider_face.py', 3 | '../_base_/default_runtime.py' 4 | ] 5 | model = dict(bbox_head=dict(num_classes=1)) 6 | # optimizer 7 | optimizer = dict(type='SGD', lr=0.012, momentum=0.9, weight_decay=5e-4) 8 | optimizer_config = dict() 9 | # learning policy 10 | lr_config = dict( 11 | policy='step', 12 | warmup='linear', 13 | warmup_iters=1000, 14 | warmup_ratio=0.001, 15 | step=[16, 20]) 16 | # runtime settings 17 | runner = dict(type='EpochBasedRunner', max_epochs=24) 18 | log_config = dict(interval=1) 19 | -------------------------------------------------------------------------------- /configs/yolact/yolact_r101_1x8_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = './yolact_r50_1x8_coco.py' 2 | 3 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 4 | -------------------------------------------------------------------------------- /configs/yolact/yolact_r50_8x8_coco.py: -------------------------------------------------------------------------------- 1 | _base_ = 'yolact_r50_1x8_coco.py' 2 | 3 | optimizer = dict(type='SGD', lr=8e-3, momentum=0.9, weight_decay=5e-4) 4 | optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2)) 5 | # learning policy 6 | lr_config = dict( 7 | policy='step', 8 | warmup='linear', 9 | warmup_iters=1000, 10 | warmup_ratio=0.1, 11 | step=[20, 42, 49, 52]) 12 | -------------------------------------------------------------------------------- /demo/demo.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/demo/demo.jpg -------------------------------------------------------------------------------- /demo/demo.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/demo/demo.mp4 -------------------------------------------------------------------------------- /demo/image_demo.py: -------------------------------------------------------------------------------- 1 | from argparse import ArgumentParser 2 | 3 | from mmdet.apis import inference_detector, init_detector, show_result_pyplot 4 | 5 | 6 | def main(): 7 | parser = ArgumentParser() 8 | parser.add_argument('img', help='Image file') 9 | parser.add_argument('config', help='Config file') 10 | parser.add_argument('checkpoint', help='Checkpoint file') 11 | parser.add_argument( 12 | '--device', default='cuda:0', help='Device used for inference') 13 | parser.add_argument( 14 | '--score-thr', type=float, default=0.3, help='bbox score threshold') 15 | args = parser.parse_args() 16 | 17 | # build the model from a config file and a checkpoint file 18 | model = init_detector(args.config, args.checkpoint, device=args.device) 19 | # test a single image 20 | result = inference_detector(model, args.img) 21 | # show the results 22 | show_result_pyplot(model, args.img, result, score_thr=args.score_thr) 23 | 24 | 25 | if __name__ == '__main__': 26 | main() 27 | -------------------------------------------------------------------------------- /docker/Dockerfile: -------------------------------------------------------------------------------- 1 | ARG PYTORCH="1.6.0" 2 | ARG CUDA="10.1" 3 | ARG CUDNN="7" 4 | 5 | FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel 6 | 7 | ENV TORCH_CUDA_ARCH_LIST="6.0 6.1 7.0+PTX" 8 | ENV TORCH_NVCC_FLAGS="-Xfatbin -compress-all" 9 | ENV CMAKE_PREFIX_PATH="$(dirname $(which conda))/../" 10 | 11 | RUN apt-get update && apt-get install -y ffmpeg libsm6 libxext6 git ninja-build libglib2.0-0 libsm6 libxrender-dev libxext6 \ 12 | && apt-get clean \ 13 | && rm -rf /var/lib/apt/lists/* 14 | 15 | # Install MMCV 16 | RUN pip install mmcv-full==latest+torch1.6.0+cu101 -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html 17 | 18 | # Install MMDetection 19 | RUN conda clean --all 20 | RUN git clone https://github.com/open-mmlab/mmdetection.git /mmdetection 21 | WORKDIR /mmdetection 22 | ENV FORCE_CUDA="1" 23 | RUN pip install -r requirements/build.txt 24 | RUN pip install --no-cache-dir -e . 25 | -------------------------------------------------------------------------------- /docker/serve/config.properties: -------------------------------------------------------------------------------- 1 | inference_address=http://0.0.0.0:8080 2 | management_address=http://0.0.0.0:8081 3 | metrics_address=http://0.0.0.0:8082 4 | model_store=/home/model-server/model-store 5 | load_models=all 6 | -------------------------------------------------------------------------------- /docker/serve/entrypoint.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | set -e 3 | 4 | if [[ "$1" = "serve" ]]; then 5 | shift 1 6 | torchserve --start --ts-config /home/model-server/config.properties 7 | else 8 | eval "$@" 9 | fi 10 | 11 | # prevent docker exit 12 | tail -f /dev/null 13 | -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- 1 | # Minimal makefile for Sphinx documentation 2 | # 3 | 4 | # You can set these variables from the command line, and also 5 | # from the environment for the first two. 6 | SPHINXOPTS ?= 7 | SPHINXBUILD ?= sphinx-build 8 | SOURCEDIR = . 9 | BUILDDIR = _build 10 | 11 | # Put it first so that "make" without argument is like "make help". 12 | help: 13 | @$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) 14 | 15 | .PHONY: help Makefile 16 | 17 | # Catch-all target: route all unknown targets to Sphinx using the new 18 | # "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS). 19 | %: Makefile 20 | @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) 21 | -------------------------------------------------------------------------------- /docs/index.rst: -------------------------------------------------------------------------------- 1 | Welcome to MMDetection's documentation! 2 | ======================================= 3 | 4 | .. toctree:: 5 | :maxdepth: 2 6 | :caption: Get Started 7 | 8 | get_started.md 9 | modelzoo_statistics.md 10 | model_zoo.md 11 | 12 | .. toctree:: 13 | :maxdepth: 2 14 | :caption: Quick Run 15 | 16 | 1_exist_data_model.md 17 | 2_new_data_model.md 18 | 19 | .. toctree:: 20 | :maxdepth: 2 21 | :caption: Tutorials 22 | 23 | tutorials/index.rst 24 | 25 | .. toctree:: 26 | :maxdepth: 2 27 | :caption: Useful Tools and Scripts 28 | 29 | useful_tools.md 30 | 31 | .. toctree:: 32 | :maxdepth: 2 33 | :caption: Notes 34 | 35 | conventions.md 36 | compatibility.md 37 | projects.md 38 | changelog.md 39 | faq.md 40 | 41 | .. toctree:: 42 | :caption: API Reference 43 | 44 | api.rst 45 | 46 | Indices and tables 47 | ================== 48 | 49 | * :ref:`genindex` 50 | * :ref:`search` 51 | -------------------------------------------------------------------------------- /docs/make.bat: -------------------------------------------------------------------------------- 1 | @ECHO OFF 2 | 3 | pushd %~dp0 4 | 5 | REM Command file for Sphinx documentation 6 | 7 | if "%SPHINXBUILD%" == "" ( 8 | set SPHINXBUILD=sphinx-build 9 | ) 10 | set SOURCEDIR=. 11 | set BUILDDIR=_build 12 | 13 | if "%1" == "" goto help 14 | 15 | %SPHINXBUILD% >NUL 2>NUL 16 | if errorlevel 9009 ( 17 | echo. 18 | echo.The 'sphinx-build' command was not found. Make sure you have Sphinx 19 | echo.installed, then set the SPHINXBUILD environment variable to point 20 | echo.to the full path of the 'sphinx-build' executable. Alternatively you 21 | echo.may add the Sphinx directory to PATH. 22 | echo. 23 | echo.If you don't have Sphinx installed, grab it from 24 | echo.http://sphinx-doc.org/ 25 | exit /b 1 26 | ) 27 | 28 | %SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O% 29 | goto end 30 | 31 | :help 32 | %SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O% 33 | 34 | :end 35 | popd 36 | -------------------------------------------------------------------------------- /docs/tutorials/index.rst: -------------------------------------------------------------------------------- 1 | .. toctree:: 2 | :maxdepth: 2 3 | 4 | config.md 5 | customize_dataset.md 6 | data_pipeline.md 7 | customize_models.md 8 | customize_runtime.md 9 | customize_losses.md 10 | finetune.md 11 | pytorch2onnx.md 12 | onnx2tensorrt.md 13 | -------------------------------------------------------------------------------- /mmcv_custom/__init__.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | from .checkpoint import load_checkpoint 4 | 5 | __all__ = ['load_checkpoint'] 6 | -------------------------------------------------------------------------------- /mmcv_custom/runner/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Open-MMLab. All rights reserved. 2 | from .checkpoint import save_checkpoint 3 | from .epoch_based_runner import EpochBasedRunnerAmp 4 | 5 | 6 | __all__ = [ 7 | 'EpochBasedRunnerAmp', 'save_checkpoint' 8 | ] 9 | -------------------------------------------------------------------------------- /mmdet/__init__.py: -------------------------------------------------------------------------------- 1 | import mmcv 2 | 3 | from .version import __version__, short_version 4 | 5 | 6 | def digit_version(version_str): 7 | digit_version = [] 8 | for x in version_str.split('.'): 9 | if x.isdigit(): 10 | digit_version.append(int(x)) 11 | elif x.find('rc') != -1: 12 | patch_version = x.split('rc') 13 | digit_version.append(int(patch_version[0]) - 1) 14 | digit_version.append(int(patch_version[1])) 15 | return digit_version 16 | 17 | 18 | mmcv_minimum_version = '1.2.4' 19 | mmcv_maximum_version = '1.4.0' 20 | mmcv_version = digit_version(mmcv.__version__) 21 | 22 | 23 | assert (mmcv_version >= digit_version(mmcv_minimum_version) 24 | and mmcv_version <= digit_version(mmcv_maximum_version)), \ 25 | f'MMCV=={mmcv.__version__} is used but incompatible. ' \ 26 | f'Please install mmcv>={mmcv_minimum_version}, <={mmcv_maximum_version}.' 27 | 28 | __all__ = ['__version__', 'short_version'] 29 | -------------------------------------------------------------------------------- /mmdet/apis/__init__.py: -------------------------------------------------------------------------------- 1 | from .inference import (async_inference_detector, inference_detector, 2 | init_detector, show_result_pyplot) 3 | from .test import multi_gpu_test, single_gpu_test 4 | from .train import get_root_logger, set_random_seed, train_detector 5 | 6 | __all__ = [ 7 | 'get_root_logger', 'set_random_seed', 'train_detector', 'init_detector', 8 | 'async_inference_detector', 'inference_detector', 'show_result_pyplot', 9 | 'multi_gpu_test', 'single_gpu_test' 10 | ] 11 | -------------------------------------------------------------------------------- /mmdet/core/__init__.py: -------------------------------------------------------------------------------- 1 | from .anchor import * # noqa: F401, F403 2 | from .bbox import * # noqa: F401, F403 3 | from .evaluation import * # noqa: F401, F403 4 | from .export import * # noqa: F401, F403 5 | from .mask import * # noqa: F401, F403 6 | from .post_processing import * # noqa: F401, F403 7 | from .utils import * # noqa: F401, F403 8 | -------------------------------------------------------------------------------- /mmdet/core/anchor/__init__.py: -------------------------------------------------------------------------------- 1 | from .anchor_generator import (AnchorGenerator, LegacyAnchorGenerator, 2 | YOLOAnchorGenerator) 3 | from .builder import ANCHOR_GENERATORS, build_anchor_generator 4 | from .point_generator import PointGenerator 5 | from .utils import anchor_inside_flags, calc_region, images_to_levels 6 | 7 | __all__ = [ 8 | 'AnchorGenerator', 'LegacyAnchorGenerator', 'anchor_inside_flags', 9 | 'PointGenerator', 'images_to_levels', 'calc_region', 10 | 'build_anchor_generator', 'ANCHOR_GENERATORS', 'YOLOAnchorGenerator' 11 | ] 12 | -------------------------------------------------------------------------------- /mmdet/core/anchor/builder.py: -------------------------------------------------------------------------------- 1 | from mmcv.utils import Registry, build_from_cfg 2 | 3 | ANCHOR_GENERATORS = Registry('Anchor generator') 4 | 5 | 6 | def build_anchor_generator(cfg, default_args=None): 7 | return build_from_cfg(cfg, ANCHOR_GENERATORS, default_args) 8 | -------------------------------------------------------------------------------- /mmdet/core/bbox/assigners/__init__.py: -------------------------------------------------------------------------------- 1 | from .approx_max_iou_assigner import ApproxMaxIoUAssigner 2 | from .assign_result import AssignResult 3 | from .atss_assigner import ATSSAssigner 4 | from .base_assigner import BaseAssigner 5 | from .center_region_assigner import CenterRegionAssigner 6 | from .grid_assigner import GridAssigner 7 | from .hungarian_assigner import HungarianAssigner 8 | from .max_iou_assigner import MaxIoUAssigner 9 | from .point_assigner import PointAssigner 10 | from .point_assigner_v2 import PointAssignerV2 11 | from .point_hm_assigner import PointHMAssigner 12 | from .atss_assigner_v2 import ATSSAssignerV2 13 | from .region_assigner import RegionAssigner 14 | 15 | __all__ = [ 16 | 'BaseAssigner', 'MaxIoUAssigner', 'ApproxMaxIoUAssigner', 'AssignResult', 17 | 'PointAssigner', 'ATSSAssigner', 'CenterRegionAssigner', 'GridAssigner', 18 | 'HungarianAssigner', 'RegionAssigner', 'PointAssignerV2', 'PointHMAssigner', 'ATSSAssignerV2' 19 | ] 20 | -------------------------------------------------------------------------------- /mmdet/core/bbox/assigners/base_assigner.py: -------------------------------------------------------------------------------- 1 | from abc import ABCMeta, abstractmethod 2 | 3 | 4 | class BaseAssigner(metaclass=ABCMeta): 5 | """Base assigner that assigns boxes to ground truth boxes.""" 6 | 7 | @abstractmethod 8 | def assign(self, bboxes, gt_bboxes, gt_bboxes_ignore=None, gt_labels=None): 9 | """Assign boxes to either a ground truth boxes or a negative boxes.""" 10 | -------------------------------------------------------------------------------- /mmdet/core/bbox/builder.py: -------------------------------------------------------------------------------- 1 | from mmcv.utils import Registry, build_from_cfg 2 | 3 | BBOX_ASSIGNERS = Registry('bbox_assigner') 4 | BBOX_SAMPLERS = Registry('bbox_sampler') 5 | BBOX_CODERS = Registry('bbox_coder') 6 | 7 | 8 | def build_assigner(cfg, **default_args): 9 | """Builder of box assigner.""" 10 | return build_from_cfg(cfg, BBOX_ASSIGNERS, default_args) 11 | 12 | 13 | def build_sampler(cfg, **default_args): 14 | """Builder of box sampler.""" 15 | return build_from_cfg(cfg, BBOX_SAMPLERS, default_args) 16 | 17 | 18 | def build_bbox_coder(cfg, **default_args): 19 | """Builder of box coder.""" 20 | return build_from_cfg(cfg, BBOX_CODERS, default_args) 21 | -------------------------------------------------------------------------------- /mmdet/core/bbox/coder/__init__.py: -------------------------------------------------------------------------------- 1 | from .base_bbox_coder import BaseBBoxCoder 2 | from .bucketing_bbox_coder import BucketingBBoxCoder 3 | from .delta_xywh_bbox_coder import DeltaXYWHBBoxCoder 4 | from .legacy_delta_xywh_bbox_coder import LegacyDeltaXYWHBBoxCoder 5 | from .pseudo_bbox_coder import PseudoBBoxCoder 6 | from .tblr_bbox_coder import TBLRBBoxCoder 7 | from .yolo_bbox_coder import YOLOBBoxCoder 8 | 9 | __all__ = [ 10 | 'BaseBBoxCoder', 'PseudoBBoxCoder', 'DeltaXYWHBBoxCoder', 11 | 'LegacyDeltaXYWHBBoxCoder', 'TBLRBBoxCoder', 'YOLOBBoxCoder', 12 | 'BucketingBBoxCoder' 13 | ] 14 | -------------------------------------------------------------------------------- /mmdet/core/bbox/coder/base_bbox_coder.py: -------------------------------------------------------------------------------- 1 | from abc import ABCMeta, abstractmethod 2 | 3 | 4 | class BaseBBoxCoder(metaclass=ABCMeta): 5 | """Base bounding box coder.""" 6 | 7 | def __init__(self, **kwargs): 8 | pass 9 | 10 | @abstractmethod 11 | def encode(self, bboxes, gt_bboxes): 12 | """Encode deltas between bboxes and ground truth boxes.""" 13 | 14 | @abstractmethod 15 | def decode(self, bboxes, bboxes_pred): 16 | """Decode the predicted bboxes according to prediction and base 17 | boxes.""" 18 | -------------------------------------------------------------------------------- /mmdet/core/bbox/coder/pseudo_bbox_coder.py: -------------------------------------------------------------------------------- 1 | from ..builder import BBOX_CODERS 2 | from .base_bbox_coder import BaseBBoxCoder 3 | 4 | 5 | @BBOX_CODERS.register_module() 6 | class PseudoBBoxCoder(BaseBBoxCoder): 7 | """Pseudo bounding box coder.""" 8 | 9 | def __init__(self, **kwargs): 10 | super(BaseBBoxCoder, self).__init__(**kwargs) 11 | 12 | def encode(self, bboxes, gt_bboxes): 13 | """torch.Tensor: return the given ``bboxes``""" 14 | return gt_bboxes 15 | 16 | def decode(self, bboxes, pred_bboxes): 17 | """torch.Tensor: return the given ``pred_bboxes``""" 18 | return pred_bboxes 19 | -------------------------------------------------------------------------------- /mmdet/core/bbox/iou_calculators/__init__.py: -------------------------------------------------------------------------------- 1 | from .builder import build_iou_calculator 2 | from .iou2d_calculator import BboxOverlaps2D, bbox_overlaps 3 | 4 | __all__ = ['build_iou_calculator', 'BboxOverlaps2D', 'bbox_overlaps'] 5 | -------------------------------------------------------------------------------- /mmdet/core/bbox/iou_calculators/builder.py: -------------------------------------------------------------------------------- 1 | from mmcv.utils import Registry, build_from_cfg 2 | 3 | IOU_CALCULATORS = Registry('IoU calculator') 4 | 5 | 6 | def build_iou_calculator(cfg, default_args=None): 7 | """Builder of IoU calculator.""" 8 | return build_from_cfg(cfg, IOU_CALCULATORS, default_args) 9 | -------------------------------------------------------------------------------- /mmdet/core/bbox/match_costs/__init__.py: -------------------------------------------------------------------------------- 1 | from .builder import build_match_cost 2 | from .match_cost import BBoxL1Cost, ClassificationCost, FocalLossCost, IoUCost 3 | 4 | __all__ = [ 5 | 'build_match_cost', 'ClassificationCost', 'BBoxL1Cost', 'IoUCost', 6 | 'FocalLossCost' 7 | ] 8 | -------------------------------------------------------------------------------- /mmdet/core/bbox/match_costs/builder.py: -------------------------------------------------------------------------------- 1 | from mmcv.utils import Registry, build_from_cfg 2 | 3 | MATCH_COST = Registry('Match Cost') 4 | 5 | 6 | def build_match_cost(cfg, default_args=None): 7 | """Builder of IoU calculator.""" 8 | return build_from_cfg(cfg, MATCH_COST, default_args) 9 | -------------------------------------------------------------------------------- /mmdet/core/bbox/samplers/__init__.py: -------------------------------------------------------------------------------- 1 | from .base_sampler import BaseSampler 2 | from .combined_sampler import CombinedSampler 3 | from .instance_balanced_pos_sampler import InstanceBalancedPosSampler 4 | from .iou_balanced_neg_sampler import IoUBalancedNegSampler 5 | from .ohem_sampler import OHEMSampler 6 | from .pseudo_sampler import PseudoSampler 7 | from .random_sampler import RandomSampler 8 | from .sampling_result import SamplingResult 9 | from .score_hlr_sampler import ScoreHLRSampler 10 | 11 | __all__ = [ 12 | 'BaseSampler', 'PseudoSampler', 'RandomSampler', 13 | 'InstanceBalancedPosSampler', 'IoUBalancedNegSampler', 'CombinedSampler', 14 | 'OHEMSampler', 'SamplingResult', 'ScoreHLRSampler' 15 | ] 16 | -------------------------------------------------------------------------------- /mmdet/core/bbox/samplers/combined_sampler.py: -------------------------------------------------------------------------------- 1 | from ..builder import BBOX_SAMPLERS, build_sampler 2 | from .base_sampler import BaseSampler 3 | 4 | 5 | @BBOX_SAMPLERS.register_module() 6 | class CombinedSampler(BaseSampler): 7 | """A sampler that combines positive sampler and negative sampler.""" 8 | 9 | def __init__(self, pos_sampler, neg_sampler, **kwargs): 10 | super(CombinedSampler, self).__init__(**kwargs) 11 | self.pos_sampler = build_sampler(pos_sampler, **kwargs) 12 | self.neg_sampler = build_sampler(neg_sampler, **kwargs) 13 | 14 | def _sample_pos(self, **kwargs): 15 | """Sample positive samples.""" 16 | raise NotImplementedError 17 | 18 | def _sample_neg(self, **kwargs): 19 | """Sample negative samples.""" 20 | raise NotImplementedError 21 | -------------------------------------------------------------------------------- /mmdet/core/evaluation/__init__.py: -------------------------------------------------------------------------------- 1 | from .class_names import (cityscapes_classes, coco_classes, dataset_aliases, 2 | get_classes, imagenet_det_classes, 3 | imagenet_vid_classes, voc_classes) 4 | from .eval_hooks import DistEvalHook, EvalHook 5 | from .mean_ap import average_precision, eval_map, print_map_summary 6 | from .recall import (eval_recalls, plot_iou_recall, plot_num_recall, 7 | print_recall_summary) 8 | 9 | __all__ = [ 10 | 'voc_classes', 'imagenet_det_classes', 'imagenet_vid_classes', 11 | 'coco_classes', 'cityscapes_classes', 'dataset_aliases', 'get_classes', 12 | 'DistEvalHook', 'EvalHook', 'average_precision', 'eval_map', 13 | 'print_map_summary', 'eval_recalls', 'print_recall_summary', 14 | 'plot_num_recall', 'plot_iou_recall' 15 | ] 16 | -------------------------------------------------------------------------------- /mmdet/core/export/__init__.py: -------------------------------------------------------------------------------- 1 | from .pytorch2onnx import (build_model_from_cfg, 2 | generate_inputs_and_wrap_model, 3 | preprocess_example_input) 4 | 5 | __all__ = [ 6 | 'build_model_from_cfg', 'generate_inputs_and_wrap_model', 7 | 'preprocess_example_input' 8 | ] 9 | -------------------------------------------------------------------------------- /mmdet/core/mask/__init__.py: -------------------------------------------------------------------------------- 1 | from .mask_target import mask_target 2 | from .structures import BaseInstanceMasks, BitmapMasks, PolygonMasks 3 | from .utils import encode_mask_results, split_combined_polys 4 | 5 | __all__ = [ 6 | 'split_combined_polys', 'mask_target', 'BaseInstanceMasks', 'BitmapMasks', 7 | 'PolygonMasks', 'encode_mask_results' 8 | ] 9 | -------------------------------------------------------------------------------- /mmdet/core/post_processing/__init__.py: -------------------------------------------------------------------------------- 1 | from .bbox_nms import fast_nms, multiclass_nms, multiclass_nms_rpd 2 | from .merge_augs import (merge_aug_bboxes, merge_aug_masks, 3 | merge_aug_proposals, merge_aug_scores) 4 | 5 | __all__ = [ 6 | 'multiclass_nms', 'merge_aug_proposals', 'merge_aug_bboxes', 7 | 'merge_aug_scores', 'merge_aug_masks', 'fast_nms', 'multiclass_nms_rpd' 8 | ] 9 | -------------------------------------------------------------------------------- /mmdet/core/utils/__init__.py: -------------------------------------------------------------------------------- 1 | from .dist_utils import DistOptimizerHook, allreduce_grads, reduce_mean 2 | from .misc import mask2ndarray, multi_apply, unmap 3 | 4 | __all__ = [ 5 | 'allreduce_grads', 'DistOptimizerHook', 'reduce_mean', 'multi_apply', 6 | 'unmap', 'mask2ndarray' 7 | ] 8 | -------------------------------------------------------------------------------- /mmdet/core/visualization/__init__.py: -------------------------------------------------------------------------------- 1 | from .image import (color_val_matplotlib, imshow_det_bboxes, 2 | imshow_gt_det_bboxes) 3 | 4 | __all__ = ['imshow_det_bboxes', 'imshow_gt_det_bboxes', 'color_val_matplotlib'] 5 | -------------------------------------------------------------------------------- /mmdet/datasets/deepfashion.py: -------------------------------------------------------------------------------- 1 | from .builder import DATASETS 2 | from .coco import CocoDataset 3 | 4 | 5 | @DATASETS.register_module() 6 | class DeepFashionDataset(CocoDataset): 7 | 8 | CLASSES = ('top', 'skirt', 'leggings', 'dress', 'outer', 'pants', 'bag', 9 | 'neckwear', 'headwear', 'eyeglass', 'belt', 'footwear', 'hair', 10 | 'skin', 'face') 11 | -------------------------------------------------------------------------------- /mmdet/datasets/samplers/__init__.py: -------------------------------------------------------------------------------- 1 | from .distributed_sampler import DistributedSampler 2 | from .group_sampler import DistributedGroupSampler, GroupSampler 3 | 4 | __all__ = ['DistributedSampler', 'DistributedGroupSampler', 'GroupSampler'] 5 | -------------------------------------------------------------------------------- /mmdet/models/__init__.py: -------------------------------------------------------------------------------- 1 | from .backbones import * # noqa: F401,F403 2 | from .builder import (BACKBONES, DETECTORS, HEADS, LOSSES, NECKS, 3 | ROI_EXTRACTORS, SHARED_HEADS, build_backbone, 4 | build_detector, build_head, build_loss, build_neck, 5 | build_roi_extractor, build_shared_head) 6 | from .dense_heads import * # noqa: F401,F403 7 | from .detectors import * # noqa: F401,F403 8 | from .losses import * # noqa: F401,F403 9 | from .necks import * # noqa: F401,F403 10 | from .roi_heads import * # noqa: F401,F403 11 | 12 | __all__ = [ 13 | 'BACKBONES', 'NECKS', 'ROI_EXTRACTORS', 'SHARED_HEADS', 'HEADS', 'LOSSES', 14 | 'DETECTORS', 'build_backbone', 'build_neck', 'build_roi_extractor', 15 | 'build_shared_head', 'build_head', 'build_loss', 'build_detector' 16 | ] 17 | -------------------------------------------------------------------------------- /mmdet/models/backbones/__init__.py: -------------------------------------------------------------------------------- 1 | from .darknet import Darknet 2 | from .detectors_resnet import DetectoRS_ResNet 3 | from .detectors_resnext import DetectoRS_ResNeXt 4 | from .hourglass import HourglassNet 5 | from .hrnet import HRNet 6 | from .regnet import RegNet 7 | from .res2net import Res2Net 8 | from .resnest import ResNeSt 9 | from .resnet import ResNet, ResNetV1d 10 | from .resnext import ResNeXt 11 | from .ssd_vgg import SSDVGG 12 | from .trident_resnet import TridentResNet 13 | from .swin_transformer import SwinTransformer 14 | 15 | __all__ = [ 16 | 'RegNet', 'ResNet', 'ResNetV1d', 'ResNeXt', 'SSDVGG', 'HRNet', 'Res2Net', 17 | 'HourglassNet', 'DetectoRS_ResNet', 'DetectoRS_ResNeXt', 'Darknet', 18 | 'ResNeSt', 'TridentResNet', 'SwinTransformer' 19 | ] 20 | -------------------------------------------------------------------------------- /mmdet/models/detectors/atss.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .single_stage import SingleStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class ATSS(SingleStageDetector): 7 | """Implementation of `ATSS `_.""" 8 | 9 | def __init__(self, 10 | backbone, 11 | neck, 12 | bbox_head, 13 | train_cfg=None, 14 | test_cfg=None, 15 | pretrained=None): 16 | super(ATSS, self).__init__(backbone, neck, bbox_head, train_cfg, 17 | test_cfg, pretrained) 18 | -------------------------------------------------------------------------------- /mmdet/models/detectors/faster_rcnn.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .two_stage import TwoStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class FasterRCNN(TwoStageDetector): 7 | """Implementation of `Faster R-CNN `_""" 8 | 9 | def __init__(self, 10 | backbone, 11 | rpn_head, 12 | roi_head, 13 | train_cfg, 14 | test_cfg, 15 | neck=None, 16 | pretrained=None): 17 | super(FasterRCNN, self).__init__( 18 | backbone=backbone, 19 | neck=neck, 20 | rpn_head=rpn_head, 21 | roi_head=roi_head, 22 | train_cfg=train_cfg, 23 | test_cfg=test_cfg, 24 | pretrained=pretrained) 25 | -------------------------------------------------------------------------------- /mmdet/models/detectors/fcos.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .single_stage import SingleStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class FCOS(SingleStageDetector): 7 | """Implementation of `FCOS `_""" 8 | 9 | def __init__(self, 10 | backbone, 11 | neck, 12 | bbox_head, 13 | train_cfg=None, 14 | test_cfg=None, 15 | pretrained=None): 16 | super(FCOS, self).__init__(backbone, neck, bbox_head, train_cfg, 17 | test_cfg, pretrained) 18 | -------------------------------------------------------------------------------- /mmdet/models/detectors/fovea.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .single_stage import SingleStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class FOVEA(SingleStageDetector): 7 | """Implementation of `FoveaBox `_""" 8 | 9 | def __init__(self, 10 | backbone, 11 | neck, 12 | bbox_head, 13 | train_cfg=None, 14 | test_cfg=None, 15 | pretrained=None): 16 | super(FOVEA, self).__init__(backbone, neck, bbox_head, train_cfg, 17 | test_cfg, pretrained) 18 | -------------------------------------------------------------------------------- /mmdet/models/detectors/fsaf.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .single_stage import SingleStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class FSAF(SingleStageDetector): 7 | """Implementation of `FSAF `_""" 8 | 9 | def __init__(self, 10 | backbone, 11 | neck, 12 | bbox_head, 13 | train_cfg=None, 14 | test_cfg=None, 15 | pretrained=None): 16 | super(FSAF, self).__init__(backbone, neck, bbox_head, train_cfg, 17 | test_cfg, pretrained) 18 | -------------------------------------------------------------------------------- /mmdet/models/detectors/gfl.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .single_stage import SingleStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class GFL(SingleStageDetector): 7 | 8 | def __init__(self, 9 | backbone, 10 | neck, 11 | bbox_head, 12 | train_cfg=None, 13 | test_cfg=None, 14 | pretrained=None): 15 | super(GFL, self).__init__(backbone, neck, bbox_head, train_cfg, 16 | test_cfg, pretrained) 17 | -------------------------------------------------------------------------------- /mmdet/models/detectors/grid_rcnn.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .two_stage import TwoStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class GridRCNN(TwoStageDetector): 7 | """Grid R-CNN. 8 | 9 | This detector is the implementation of: 10 | - Grid R-CNN (https://arxiv.org/abs/1811.12030) 11 | - Grid R-CNN Plus: Faster and Better (https://arxiv.org/abs/1906.05688) 12 | """ 13 | 14 | def __init__(self, 15 | backbone, 16 | rpn_head, 17 | roi_head, 18 | train_cfg, 19 | test_cfg, 20 | neck=None, 21 | pretrained=None): 22 | super(GridRCNN, self).__init__( 23 | backbone=backbone, 24 | neck=neck, 25 | rpn_head=rpn_head, 26 | roi_head=roi_head, 27 | train_cfg=train_cfg, 28 | test_cfg=test_cfg, 29 | pretrained=pretrained) 30 | -------------------------------------------------------------------------------- /mmdet/models/detectors/htc.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .cascade_rcnn import CascadeRCNN 3 | 4 | 5 | @DETECTORS.register_module() 6 | class HybridTaskCascade(CascadeRCNN): 7 | """Implementation of `HTC `_""" 8 | 9 | def __init__(self, **kwargs): 10 | super(HybridTaskCascade, self).__init__(**kwargs) 11 | 12 | @property 13 | def with_semantic(self): 14 | """bool: whether the detector has a semantic head""" 15 | return self.roi_head.with_semantic 16 | -------------------------------------------------------------------------------- /mmdet/models/detectors/mask_rcnn.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .two_stage import TwoStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class MaskRCNN(TwoStageDetector): 7 | """Implementation of `Mask R-CNN `_""" 8 | 9 | def __init__(self, 10 | backbone, 11 | rpn_head, 12 | roi_head, 13 | train_cfg, 14 | test_cfg, 15 | neck=None, 16 | pretrained=None): 17 | super(MaskRCNN, self).__init__( 18 | backbone=backbone, 19 | neck=neck, 20 | rpn_head=rpn_head, 21 | roi_head=roi_head, 22 | train_cfg=train_cfg, 23 | test_cfg=test_cfg, 24 | pretrained=pretrained) 25 | -------------------------------------------------------------------------------- /mmdet/models/detectors/mask_scoring_rcnn.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .two_stage import TwoStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class MaskScoringRCNN(TwoStageDetector): 7 | """Mask Scoring RCNN. 8 | 9 | https://arxiv.org/abs/1903.00241 10 | """ 11 | 12 | def __init__(self, 13 | backbone, 14 | rpn_head, 15 | roi_head, 16 | train_cfg, 17 | test_cfg, 18 | neck=None, 19 | pretrained=None): 20 | super(MaskScoringRCNN, self).__init__( 21 | backbone=backbone, 22 | neck=neck, 23 | rpn_head=rpn_head, 24 | roi_head=roi_head, 25 | train_cfg=train_cfg, 26 | test_cfg=test_cfg, 27 | pretrained=pretrained) 28 | -------------------------------------------------------------------------------- /mmdet/models/detectors/nasfcos.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .single_stage import SingleStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class NASFCOS(SingleStageDetector): 7 | """NAS-FCOS: Fast Neural Architecture Search for Object Detection. 8 | 9 | https://arxiv.org/abs/1906.0442 10 | """ 11 | 12 | def __init__(self, 13 | backbone, 14 | neck, 15 | bbox_head, 16 | train_cfg=None, 17 | test_cfg=None, 18 | pretrained=None): 19 | super(NASFCOS, self).__init__(backbone, neck, bbox_head, train_cfg, 20 | test_cfg, pretrained) 21 | -------------------------------------------------------------------------------- /mmdet/models/detectors/paa.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .single_stage import SingleStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class PAA(SingleStageDetector): 7 | """Implementation of `PAA `_.""" 8 | 9 | def __init__(self, 10 | backbone, 11 | neck, 12 | bbox_head, 13 | train_cfg=None, 14 | test_cfg=None, 15 | pretrained=None): 16 | super(PAA, self).__init__(backbone, neck, bbox_head, train_cfg, 17 | test_cfg, pretrained) 18 | -------------------------------------------------------------------------------- /mmdet/models/detectors/point_rend.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .two_stage import TwoStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class PointRend(TwoStageDetector): 7 | """PointRend: Image Segmentation as Rendering 8 | 9 | This detector is the implementation of 10 | `PointRend `_. 11 | 12 | """ 13 | 14 | def __init__(self, 15 | backbone, 16 | rpn_head, 17 | roi_head, 18 | train_cfg, 19 | test_cfg, 20 | neck=None, 21 | pretrained=None): 22 | super(PointRend, self).__init__( 23 | backbone=backbone, 24 | neck=neck, 25 | rpn_head=rpn_head, 26 | roi_head=roi_head, 27 | train_cfg=train_cfg, 28 | test_cfg=test_cfg, 29 | pretrained=pretrained) 30 | -------------------------------------------------------------------------------- /mmdet/models/detectors/reppoints_detector.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .single_stage import SingleStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class RepPointsDetector(SingleStageDetector): 7 | """RepPoints: Point Set Representation for Object Detection. 8 | 9 | This detector is the implementation of: 10 | - RepPoints detector (https://arxiv.org/pdf/1904.11490) 11 | """ 12 | 13 | def __init__(self, 14 | backbone, 15 | neck, 16 | bbox_head, 17 | train_cfg=None, 18 | test_cfg=None, 19 | pretrained=None): 20 | super(RepPointsDetector, 21 | self).__init__(backbone, neck, bbox_head, train_cfg, test_cfg, 22 | pretrained) 23 | -------------------------------------------------------------------------------- /mmdet/models/detectors/retinanet.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .single_stage import SingleStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class RetinaNet(SingleStageDetector): 7 | """Implementation of `RetinaNet `_""" 8 | 9 | def __init__(self, 10 | backbone, 11 | neck, 12 | bbox_head, 13 | train_cfg=None, 14 | test_cfg=None, 15 | pretrained=None): 16 | super(RetinaNet, self).__init__(backbone, neck, bbox_head, train_cfg, 17 | test_cfg, pretrained) 18 | -------------------------------------------------------------------------------- /mmdet/models/detectors/scnet.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .cascade_rcnn import CascadeRCNN 3 | 4 | 5 | @DETECTORS.register_module() 6 | class SCNet(CascadeRCNN): 7 | """Implementation of `SCNet `_""" 8 | 9 | def __init__(self, **kwargs): 10 | super(SCNet, self).__init__(**kwargs) 11 | -------------------------------------------------------------------------------- /mmdet/models/detectors/vfnet.py: -------------------------------------------------------------------------------- 1 | from ..builder import DETECTORS 2 | from .single_stage import SingleStageDetector 3 | 4 | 5 | @DETECTORS.register_module() 6 | class VFNet(SingleStageDetector): 7 | """Implementation of `VarifocalNet 8 | (VFNet).`_""" 9 | 10 | def __init__(self, 11 | backbone, 12 | neck, 13 | bbox_head, 14 | train_cfg=None, 15 | test_cfg=None, 16 | pretrained=None): 17 | super(VFNet, self).__init__(backbone, neck, bbox_head, train_cfg, 18 | test_cfg, pretrained) 19 | -------------------------------------------------------------------------------- /mmdet/models/detectors/yolo.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) 2019 Western Digital Corporation or its affiliates. 2 | 3 | from ..builder import DETECTORS 4 | from .single_stage import SingleStageDetector 5 | 6 | 7 | @DETECTORS.register_module() 8 | class YOLOV3(SingleStageDetector): 9 | 10 | def __init__(self, 11 | backbone, 12 | neck, 13 | bbox_head, 14 | train_cfg=None, 15 | test_cfg=None, 16 | pretrained=None): 17 | super(YOLOV3, self).__init__(backbone, neck, bbox_head, train_cfg, 18 | test_cfg, pretrained) 19 | -------------------------------------------------------------------------------- /mmdet/models/necks/__init__.py: -------------------------------------------------------------------------------- 1 | from .bfp import BFP 2 | from .channel_mapper import ChannelMapper 3 | from .fpg import FPG 4 | from .fpn import FPN 5 | from .fpn_carafe import FPN_CARAFE 6 | from .hrfpn import HRFPN 7 | from .nas_fpn import NASFPN 8 | from .nasfcos_fpn import NASFCOS_FPN 9 | from .pafpn import PAFPN 10 | from .rfp import RFP 11 | from .bifpn import BiFPN 12 | from .yolo_neck import YOLOV3Neck 13 | 14 | __all__ = [ 15 | 'FPN', 'BFP', 'ChannelMapper', 'HRFPN', 'NASFPN', 'FPN_CARAFE', 'PAFPN', 16 | 'NASFCOS_FPN', 'RFP', 'YOLOV3Neck', 'FPG', 'BiFPN' 17 | ] 18 | -------------------------------------------------------------------------------- /mmdet/models/roi_heads/bbox_heads/__init__.py: -------------------------------------------------------------------------------- 1 | from .bbox_head import BBoxHead 2 | from .convfc_bbox_head import (ConvFCBBoxHead, Shared2FCBBoxHead, 3 | Shared4Conv1FCBBoxHead) 4 | from .dii_head import DIIHead 5 | from .double_bbox_head import DoubleConvFCBBoxHead 6 | from .sabl_head import SABLHead 7 | from .scnet_bbox_head import SCNetBBoxHead 8 | 9 | __all__ = [ 10 | 'BBoxHead', 'ConvFCBBoxHead', 'Shared2FCBBoxHead', 11 | 'Shared4Conv1FCBBoxHead', 'DoubleConvFCBBoxHead', 'SABLHead', 'DIIHead', 12 | 'SCNetBBoxHead' 13 | ] 14 | -------------------------------------------------------------------------------- /mmdet/models/roi_heads/mask_heads/__init__.py: -------------------------------------------------------------------------------- 1 | from .coarse_mask_head import CoarseMaskHead 2 | from .fcn_mask_head import FCNMaskHead 3 | from .feature_relay_head import FeatureRelayHead 4 | from .fused_semantic_head import FusedSemanticHead 5 | from .global_context_head import GlobalContextHead 6 | from .grid_head import GridHead 7 | from .htc_mask_head import HTCMaskHead 8 | from .mask_point_head import MaskPointHead 9 | from .maskiou_head import MaskIoUHead 10 | from .scnet_mask_head import SCNetMaskHead 11 | from .scnet_semantic_head import SCNetSemanticHead 12 | from .condconv_mask_head import CondConvMaskHead 13 | 14 | __all__ = [ 15 | 'FCNMaskHead', 'HTCMaskHead', 'FusedSemanticHead', 'GridHead', 16 | 'MaskIoUHead', 'CoarseMaskHead', 'MaskPointHead', 'SCNetMaskHead', 17 | 'SCNetSemanticHead', 'GlobalContextHead', 'FeatureRelayHead', 'CondConvMaskHead' 18 | ] 19 | -------------------------------------------------------------------------------- /mmdet/models/roi_heads/roi_extractors/__init__.py: -------------------------------------------------------------------------------- 1 | from .generic_roi_extractor import GenericRoIExtractor 2 | from .single_level_roi_extractor import SingleRoIExtractor 3 | 4 | __all__ = [ 5 | 'SingleRoIExtractor', 6 | 'GenericRoIExtractor', 7 | ] 8 | -------------------------------------------------------------------------------- /mmdet/models/roi_heads/shared_heads/__init__.py: -------------------------------------------------------------------------------- 1 | from .res_layer import ResLayer 2 | 3 | __all__ = ['ResLayer'] 4 | -------------------------------------------------------------------------------- /mmdet/models/utils/__init__.py: -------------------------------------------------------------------------------- 1 | from .builder import build_positional_encoding, build_transformer 2 | from .gaussian_target import gaussian_radius, gen_gaussian_target 3 | from .positional_encoding import (LearnedPositionalEncoding, 4 | SinePositionalEncoding) 5 | from .res_layer import ResLayer, SimplifiedBasicBlock 6 | from .transformer import (FFN, DynamicConv, MultiheadAttention, Transformer, 7 | TransformerDecoder, TransformerDecoderLayer, 8 | TransformerEncoder, TransformerEncoderLayer) 9 | 10 | __all__ = [ 11 | 'ResLayer', 'gaussian_radius', 'gen_gaussian_target', 'MultiheadAttention', 12 | 'FFN', 'TransformerEncoderLayer', 'TransformerEncoder', 13 | 'TransformerDecoderLayer', 'TransformerDecoder', 'Transformer', 14 | 'build_transformer', 'build_positional_encoding', 'SinePositionalEncoding', 15 | 'LearnedPositionalEncoding', 'DynamicConv', 'SimplifiedBasicBlock' 16 | ] 17 | -------------------------------------------------------------------------------- /mmdet/models/utils/builder.py: -------------------------------------------------------------------------------- 1 | from mmcv.utils import Registry, build_from_cfg 2 | 3 | TRANSFORMER = Registry('Transformer') 4 | POSITIONAL_ENCODING = Registry('Position encoding') 5 | 6 | 7 | def build_transformer(cfg, default_args=None): 8 | """Builder for Transformer.""" 9 | return build_from_cfg(cfg, TRANSFORMER, default_args) 10 | 11 | 12 | def build_positional_encoding(cfg, default_args=None): 13 | """Builder for Position Encoding.""" 14 | return build_from_cfg(cfg, POSITIONAL_ENCODING, default_args) 15 | -------------------------------------------------------------------------------- /mmdet/utils/__init__.py: -------------------------------------------------------------------------------- 1 | from .collect_env import collect_env 2 | from .logger import get_root_logger 3 | from .optimizer import DistOptimizerHook 4 | 5 | __all__ = ['get_root_logger', 'collect_env', 'DistOptimizerHook'] 6 | -------------------------------------------------------------------------------- /mmdet/utils/collect_env.py: -------------------------------------------------------------------------------- 1 | from mmcv.utils import collect_env as collect_base_env 2 | from mmcv.utils import get_git_hash 3 | 4 | import mmdet 5 | 6 | 7 | def collect_env(): 8 | """Collect the information of the running environments.""" 9 | env_info = collect_base_env() 10 | env_info['MMDetection'] = mmdet.__version__ + '+' + get_git_hash()[:7] 11 | return env_info 12 | 13 | 14 | if __name__ == '__main__': 15 | for name, val in collect_env().items(): 16 | print(f'{name}: {val}') 17 | -------------------------------------------------------------------------------- /mmdet/utils/common.py: -------------------------------------------------------------------------------- 1 | import torch 2 | def compute_locations(h, w, stride, device): 3 | shifts_x = torch.arange( 4 | 0, w * stride, step=stride, 5 | dtype=torch.float32, device=device 6 | ) 7 | shifts_y = torch.arange( 8 | 0, h * stride, step=stride, 9 | dtype=torch.float32, device=device 10 | ) 11 | shift_y, shift_x = torch.meshgrid(shifts_y, shifts_x) 12 | shift_x = shift_x.reshape(-1) 13 | shift_y = shift_y.reshape(-1) 14 | locations = torch.stack((shift_x, shift_y), dim=1) + stride // 2 15 | return locations 16 | -------------------------------------------------------------------------------- /mmdet/utils/logger.py: -------------------------------------------------------------------------------- 1 | import logging 2 | 3 | from mmcv.utils import get_logger 4 | 5 | 6 | def get_root_logger(log_file=None, log_level=logging.INFO): 7 | """Get root logger. 8 | 9 | Args: 10 | log_file (str, optional): File path of log. Defaults to None. 11 | log_level (int, optional): The level of logger. 12 | Defaults to logging.INFO. 13 | 14 | Returns: 15 | :obj:`logging.Logger`: The obtained logger 16 | """ 17 | logger = get_logger(name='mmdet', log_file=log_file, log_level=log_level) 18 | 19 | return logger 20 | -------------------------------------------------------------------------------- /mmdet/version.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Open-MMLab. All rights reserved. 2 | 3 | __version__ = '2.11.0' 4 | short_version = __version__ 5 | 6 | 7 | def parse_version_info(version_str): 8 | version_info = [] 9 | for x in version_str.split('.'): 10 | if x.isdigit(): 11 | version_info.append(int(x)) 12 | elif x.find('rc') != -1: 13 | patch_version = x.split('rc') 14 | version_info.append(int(patch_version[0])) 15 | version_info.append(f'rc{patch_version[1]}') 16 | return tuple(version_info) 17 | 18 | 19 | version_info = parse_version_info(__version__) 20 | -------------------------------------------------------------------------------- /pytest.ini: -------------------------------------------------------------------------------- 1 | [pytest] 2 | addopts = --xdoctest --xdoctest-style=auto 3 | norecursedirs = .git ignore build __pycache__ data docker docs .eggs 4 | 5 | filterwarnings= default 6 | ignore:.*No cfgstr given in Cacher constructor or call.*:Warning 7 | ignore:.*Define the __nice__ method for.*:Warning 8 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | -r requirements/build.txt 2 | -r requirements/optional.txt 3 | -r requirements/runtime.txt 4 | -r requirements/tests.txt 5 | -------------------------------------------------------------------------------- /requirements/build.txt: -------------------------------------------------------------------------------- 1 | # These must be installed before building mmdetection 2 | cython 3 | numpy 4 | -------------------------------------------------------------------------------- /requirements/docs.txt: -------------------------------------------------------------------------------- 1 | recommonmark 2 | sphinx 3 | sphinx_markdown_tables 4 | sphinx_rtd_theme 5 | -------------------------------------------------------------------------------- /requirements/optional.txt: -------------------------------------------------------------------------------- 1 | albumentations>=0.3.2 2 | cityscapesscripts 3 | imagecorruptions 4 | mmlvis 5 | scipy 6 | sklearn 7 | -------------------------------------------------------------------------------- /requirements/readthedocs.txt: -------------------------------------------------------------------------------- 1 | mmcv 2 | torch 3 | torchvision 4 | -------------------------------------------------------------------------------- /requirements/runtime.txt: -------------------------------------------------------------------------------- 1 | matplotlib 2 | mmpycocotools 3 | numpy 4 | six 5 | terminaltables 6 | timm 7 | -------------------------------------------------------------------------------- /requirements/tests.txt: -------------------------------------------------------------------------------- 1 | asynctest 2 | codecov 3 | flake8 4 | interrogate 5 | isort==4.3.21 6 | # Note: used for kwarray.group_items, this may be ported to mmcv in the future. 7 | kwarray 8 | onnx==1.7.0 9 | onnxruntime==1.5.1 10 | pytest 11 | ubelt 12 | xdoctest>=0.10.0 13 | yapf 14 | -------------------------------------------------------------------------------- /resources/coco_test_12510.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/resources/coco_test_12510.jpg -------------------------------------------------------------------------------- /resources/corruptions_sev_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/resources/corruptions_sev_3.png -------------------------------------------------------------------------------- /resources/data_pipeline.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/resources/data_pipeline.png -------------------------------------------------------------------------------- /resources/loss_curve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/resources/loss_curve.png -------------------------------------------------------------------------------- /resources/mmdet-logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/resources/mmdet-logo.png -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- 1 | [isort] 2 | line_length = 79 3 | multi_line_output = 0 4 | known_standard_library = setuptools 5 | known_first_party = mmdet 6 | known_third_party = PIL,asynctest,cityscapesscripts,cv2,gather_models,matplotlib,mmcv,numpy,onnx,onnxruntime,pycocotools,pytest,seaborn,six,terminaltables,torch,ts 7 | no_lines_before = STDLIB,LOCALFOLDER 8 | default_section = THIRDPARTY 9 | 10 | [yapf] 11 | BASED_ON_STYLE = pep8 12 | BLANK_LINE_BEFORE_NESTED_CLASS_OR_DEF = true 13 | SPLIT_BEFORE_EXPRESSION_AFTER_OPENING_PAREN = true 14 | -------------------------------------------------------------------------------- /tests/data/VOCdevkit/VOC2007/ImageSets/Main/test.txt: -------------------------------------------------------------------------------- 1 | 000001 2 | -------------------------------------------------------------------------------- /tests/data/VOCdevkit/VOC2007/ImageSets/Main/trainval.txt: -------------------------------------------------------------------------------- 1 | 000001 2 | -------------------------------------------------------------------------------- /tests/data/VOCdevkit/VOC2007/JPEGImages/000001.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/tests/data/VOCdevkit/VOC2007/JPEGImages/000001.jpg -------------------------------------------------------------------------------- /tests/data/VOCdevkit/VOC2012/Annotations/000001.xml: -------------------------------------------------------------------------------- 1 | 2 | VOC2007 3 | 000002.jpg 4 | 5 | The VOC2007 Database 6 | PASCAL VOC2007 7 | flickr 8 | 329145082 9 | 10 | 11 | hiromori2 12 | Hiroyuki Mori 13 | 14 | 15 | 335 16 | 500 17 | 3 18 | 19 | 0 20 | 21 | train 22 | Unspecified 23 | 0 24 | 0 25 | 26 | 139 27 | 200 28 | 207 29 | 301 30 | 31 | 32 | 33 | -------------------------------------------------------------------------------- /tests/data/VOCdevkit/VOC2012/ImageSets/Main/test.txt: -------------------------------------------------------------------------------- 1 | 000001 2 | -------------------------------------------------------------------------------- /tests/data/VOCdevkit/VOC2012/ImageSets/Main/trainval.txt: -------------------------------------------------------------------------------- 1 | 000001 2 | -------------------------------------------------------------------------------- /tests/data/VOCdevkit/VOC2012/JPEGImages/000001.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/tests/data/VOCdevkit/VOC2012/JPEGImages/000001.jpg -------------------------------------------------------------------------------- /tests/data/color.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/tests/data/color.jpg -------------------------------------------------------------------------------- /tests/data/gray.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/tests/data/gray.jpg -------------------------------------------------------------------------------- /tests/test_data/test_datasets/test_xml_dataset.py: -------------------------------------------------------------------------------- 1 | import pytest 2 | 3 | from mmdet.datasets import DATASETS 4 | 5 | 6 | def test_xml_dataset(): 7 | dataconfig = { 8 | 'ann_file': 'data/VOCdevkit/VOC2007/ImageSets/Main/test.txt', 9 | 'img_prefix': 'data/VOCdevkit/VOC2007/', 10 | 'pipeline': [{ 11 | 'type': 'LoadImageFromFile' 12 | }] 13 | } 14 | XMLDataset = DATASETS.get('XMLDataset') 15 | 16 | class XMLDatasetSubClass(XMLDataset): 17 | CLASSES = None 18 | 19 | # get_ann_info and _filter_imgs of XMLDataset 20 | # would use self.CLASSES, we added CLASSES not NONE 21 | with pytest.raises(AssertionError): 22 | XMLDatasetSubClass(**dataconfig) 23 | -------------------------------------------------------------------------------- /tests/test_data/test_pipelines/test_formatting.py: -------------------------------------------------------------------------------- 1 | import os.path as osp 2 | 3 | from mmcv.utils import build_from_cfg 4 | 5 | from mmdet.datasets.builder import PIPELINES 6 | 7 | 8 | def test_default_format_bundle(): 9 | results = dict( 10 | img_prefix=osp.join(osp.dirname(__file__), '../../data'), 11 | img_info=dict(filename='color.jpg')) 12 | load = dict(type='LoadImageFromFile') 13 | load = build_from_cfg(load, PIPELINES) 14 | bundle = dict(type='DefaultFormatBundle') 15 | bundle = build_from_cfg(bundle, PIPELINES) 16 | results = load(results) 17 | assert 'pad_shape' not in results 18 | assert 'scale_factor' not in results 19 | assert 'img_norm_cfg' not in results 20 | results = bundle(results) 21 | assert 'pad_shape' in results 22 | assert 'scale_factor' in results 23 | assert 'img_norm_cfg' in results 24 | -------------------------------------------------------------------------------- /tests/test_models/test_backbones/__init__.py: -------------------------------------------------------------------------------- 1 | from .utils import check_norm_state, is_block, is_norm 2 | 3 | __all__ = ['is_block', 'is_norm', 'check_norm_state'] 4 | -------------------------------------------------------------------------------- /tests/test_models/test_roi_heads/__init__.py: -------------------------------------------------------------------------------- 1 | from .utils import _dummy_bbox_sampling 2 | 3 | __all__ = ['_dummy_bbox_sampling'] 4 | -------------------------------------------------------------------------------- /tests/test_onnx/__init__.py: -------------------------------------------------------------------------------- 1 | from .utils import (WrapFunction, convert_result_list, ort_validate, 2 | verify_model) 3 | 4 | __all__ = [ 5 | 'WrapFunction', 'verify_model', 'convert_result_list', 'ort_validate' 6 | ] 7 | -------------------------------------------------------------------------------- /tests/test_onnx/data/retina_head_get_bboxes.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/tests/test_onnx/data/retina_head_get_bboxes.pkl -------------------------------------------------------------------------------- /tests/test_onnx/data/yolov3_head_get_bboxes.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/tests/test_onnx/data/yolov3_head_get_bboxes.pkl -------------------------------------------------------------------------------- /tests/test_onnx/data/yolov3_neck.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SwinTransformer/Swin-Transformer-Object-Detection/c7b20110addde0f74b1fbf812b403d16a59a87a9/tests/test_onnx/data/yolov3_neck.pkl -------------------------------------------------------------------------------- /tests/test_utils/test_version.py: -------------------------------------------------------------------------------- 1 | from mmdet import digit_version 2 | 3 | 4 | def test_version_check(): 5 | assert digit_version('1.0.5') > digit_version('1.0.5rc0') 6 | assert digit_version('1.0.5') > digit_version('1.0.4rc0') 7 | assert digit_version('1.0.5') > digit_version('1.0rc0') 8 | assert digit_version('1.0.0') > digit_version('0.6.2') 9 | assert digit_version('1.0.0') > digit_version('0.2.16') 10 | assert digit_version('1.0.5rc0') > digit_version('1.0.0rc0') 11 | assert digit_version('1.0.0rc1') > digit_version('1.0.0rc0') 12 | assert digit_version('1.0.0rc2') > digit_version('1.0.0rc0') 13 | assert digit_version('1.0.0rc2') > digit_version('1.0.0rc1') 14 | assert digit_version('1.0.1rc1') > digit_version('1.0.0rc1') 15 | assert digit_version('1.0.0') > digit_version('1.0.0rc1') 16 | -------------------------------------------------------------------------------- /tools/dist_test.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | CONFIG=$1 4 | CHECKPOINT=$2 5 | GPUS=$3 6 | PORT=${PORT:-29500} 7 | 8 | PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \ 9 | python -m torch.distributed.launch --nproc_per_node=$GPUS --master_port=$PORT \ 10 | $(dirname "$0")/test.py $CONFIG $CHECKPOINT --launcher pytorch ${@:4} 11 | -------------------------------------------------------------------------------- /tools/dist_train.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | CONFIG=$1 4 | GPUS=$2 5 | PORT=${PORT:-29500} 6 | 7 | PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \ 8 | python -m torch.distributed.launch --nproc_per_node=$GPUS --master_port=$PORT \ 9 | $(dirname "$0")/train.py $CONFIG --launcher pytorch ${@:3} 10 | -------------------------------------------------------------------------------- /tools/slurm_test.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | set -x 4 | 5 | PARTITION=$1 6 | JOB_NAME=$2 7 | CONFIG=$3 8 | CHECKPOINT=$4 9 | GPUS=${GPUS:-8} 10 | GPUS_PER_NODE=${GPUS_PER_NODE:-8} 11 | CPUS_PER_TASK=${CPUS_PER_TASK:-5} 12 | PY_ARGS=${@:5} 13 | SRUN_ARGS=${SRUN_ARGS:-""} 14 | 15 | PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \ 16 | srun -p ${PARTITION} \ 17 | --job-name=${JOB_NAME} \ 18 | --gres=gpu:${GPUS_PER_NODE} \ 19 | --ntasks=${GPUS} \ 20 | --ntasks-per-node=${GPUS_PER_NODE} \ 21 | --cpus-per-task=${CPUS_PER_TASK} \ 22 | --kill-on-bad-exit=1 \ 23 | ${SRUN_ARGS} \ 24 | python -u tools/test.py ${CONFIG} ${CHECKPOINT} --launcher="slurm" ${PY_ARGS} 25 | -------------------------------------------------------------------------------- /tools/slurm_train.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | set -x 4 | 5 | PARTITION=$1 6 | JOB_NAME=$2 7 | CONFIG=$3 8 | WORK_DIR=$4 9 | GPUS=${GPUS:-8} 10 | GPUS_PER_NODE=${GPUS_PER_NODE:-8} 11 | CPUS_PER_TASK=${CPUS_PER_TASK:-5} 12 | SRUN_ARGS=${SRUN_ARGS:-""} 13 | PY_ARGS=${@:5} 14 | 15 | PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \ 16 | srun -p ${PARTITION} \ 17 | --job-name=${JOB_NAME} \ 18 | --gres=gpu:${GPUS_PER_NODE} \ 19 | --ntasks=${GPUS} \ 20 | --ntasks-per-node=${GPUS_PER_NODE} \ 21 | --cpus-per-task=${CPUS_PER_TASK} \ 22 | --kill-on-bad-exit=1 \ 23 | ${SRUN_ARGS} \ 24 | python -u tools/train.py ${CONFIG} --work-dir=${WORK_DIR} --launcher="slurm" ${PY_ARGS} 25 | --------------------------------------------------------------------------------