├── .circleci ├── config.yml ├── docker │ └── Dockerfile └── test.yml ├── .dev_scripts ├── benchmark_full_models.txt ├── benchmark_options.py ├── benchmark_train_models.txt ├── covignore.cfg ├── diff_coverage_test.sh ├── gather_models.py ├── gen_benchmark_script.py ├── linter.sh ├── test_benchmark.sh └── train_benchmark.sh ├── .github ├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── ISSUE_TEMPLATE │ ├── 1-bug-report.yml │ ├── 2-feature_request.yml │ ├── 3-new-model.yml │ ├── 4-documentation.yml │ └── config.yml ├── pull_request_template.md └── workflows │ ├── deploy.yml │ ├── lint.yml │ ├── merge_stage_test.yml │ ├── pr_stage_test.yml │ └── test_mim.yml ├── .gitignore ├── .pre-commit-config-zh-cn.yaml ├── .pre-commit-config.yaml ├── .readthedocs.yml ├── CITATION.cff ├── LICENSE ├── MANIFEST.in ├── README.md ├── README_zh-CN.md ├── configs ├── 3dssd │ ├── 3dssd_4xb4_kitti-3d-car.py │ ├── README.md │ └── metafile.yml ├── _base_ │ ├── datasets │ │ ├── kitti-3d-3class.py │ │ ├── kitti-3d-car.py │ │ ├── kitti-mono3d.py │ │ ├── lyft-3d-range100.py │ │ ├── lyft-3d.py │ │ ├── nuim-instance.py │ │ ├── nus-3d.py │ │ ├── nus-mono3d.py │ │ ├── s3dis-3d.py │ │ ├── s3dis-seg.py │ │ ├── scannet-3d.py │ │ ├── scannet-seg.py │ │ ├── semantickitti.py │ │ ├── sunrgbd-3d.py │ │ ├── waymoD3-fov-mono3d-3class.py │ │ ├── waymoD3-mv-mono3d-3class.py │ │ ├── waymoD5-3d-3class.py │ │ ├── waymoD5-3d-car.py │ │ ├── waymoD5-fov-mono3d-3class.py │ │ ├── waymoD5-mv-mono3d-3class.py │ │ └── waymoD5-mv3d-3class.py │ ├── default_runtime.py │ ├── models │ │ ├── 3dssd.py │ │ ├── cascade-mask-rcnn_r50_fpn.py │ │ ├── centerpoint_pillar02_second_secfpn_nus.py │ │ ├── centerpoint_voxel01_second_secfpn_nus.py │ │ ├── cylinder3d.py │ │ ├── dgcnn.py │ │ ├── fcaf3d.py │ │ ├── fcos3d.py │ │ ├── groupfree3d.py │ │ ├── h3dnet.py │ │ ├── imvotenet.py │ │ ├── mask-rcnn_r50_fpn.py │ │ ├── minkunet.py │ │ ├── multiview_dfm.py │ │ ├── paconv_ssg-cuda.py │ │ ├── paconv_ssg.py │ │ ├── parta2.py │ │ ├── pgd.py │ │ ├── point_rcnn.py │ │ ├── pointnet2_msg.py │ │ ├── pointnet2_ssg.py │ │ ├── pointpillars_hv_fpn_lyft.py │ │ ├── pointpillars_hv_fpn_nus.py │ │ ├── pointpillars_hv_fpn_range100_lyft.py │ │ ├── pointpillars_hv_secfpn_kitti.py │ │ ├── pointpillars_hv_secfpn_waymo.py │ │ ├── second_hv_secfpn_kitti.py │ │ ├── second_hv_secfpn_waymo.py │ │ ├── smoke.py │ │ ├── spvcnn.py │ │ └── votenet.py │ └── schedules │ │ ├── cosine.py │ │ ├── cyclic-20e.py │ │ ├── cyclic-40e.py │ │ ├── mmdet-schedule-1x.py │ │ ├── schedule-2x.py │ │ ├── schedule-3x.py │ │ ├── seg-cosine-100e.py │ │ ├── seg-cosine-150e.py │ │ ├── seg-cosine-200e.py │ │ └── seg-cosine-50e.py ├── benchmark │ ├── hv_PartA2_secfpn_4x8_cyclic_80e_pcdet_kitti-3d-3class.py │ ├── hv_pointpillars_secfpn_3x8_100e_det3d_kitti-3d-car.py │ ├── hv_pointpillars_secfpn_4x8_80e_pcdet_kitti-3d-3class.py │ └── hv_second_secfpn_4x8_80e_pcdet_kitti-3d-3class.py ├── centerpoint │ ├── README.md │ ├── centerpoint_pillar02_second_secfpn_8xb4-cyclic-20e_nus-3d.py │ ├── centerpoint_pillar02_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d.py │ ├── centerpoint_pillar02_second_secfpn_head-dcn-circlenms_8xb4-cyclic-20e_nus-3d.py │ ├── centerpoint_pillar02_second_secfpn_head-dcn_8xb4-cyclic-20e_nus-3d.py │ ├── centerpoint_voxel0075_second_secfpn_8xb4-cyclic-20e_nus-3d.py │ ├── centerpoint_voxel0075_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d.py │ ├── centerpoint_voxel0075_second_secfpn_head-dcn-circlenms_8xb4-cyclic-20e_nus-3d.py │ ├── centerpoint_voxel0075_second_secfpn_head-dcn-circlenms_8xb4-flip-tta-cyclic-20e_nus-3d.py │ ├── centerpoint_voxel0075_second_secfpn_head-dcn_8xb4-cyclic-20e_nus-3d.py │ ├── centerpoint_voxel0075_second_secfpn_head-dcn_8xb4-flip-tta-cyclic-20e_nus-3d.py │ ├── centerpoint_voxel0075_second_secfpn_head-dcn_8xb4-tta-cyclic-20e_nus-3d.py │ ├── centerpoint_voxel01_second_secfpn_8xb4-cyclic-20e_nus-3d.py │ ├── centerpoint_voxel01_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d.py │ ├── centerpoint_voxel01_second_secfpn_head-dcn-circlenms_8xb4-cyclic-20e_nus-3d.py │ ├── centerpoint_voxel01_second_secfpn_head-dcn_8xb4-cyclic-20e_nus-3d.py │ └── metafile.yml ├── cylinder3d │ ├── README.md │ ├── cylinder3d_4xb4-3x_semantickitti.py │ ├── cylinder3d_8xb2-laser-polar-mix-3x_semantickitti.py │ └── metafile.yml ├── dgcnn │ ├── README.md │ ├── dgcnn_4xb32-cosine-100e_s3dis-seg_test-area1.py │ ├── dgcnn_4xb32-cosine-100e_s3dis-seg_test-area2.py │ ├── dgcnn_4xb32-cosine-100e_s3dis-seg_test-area3.py │ ├── dgcnn_4xb32-cosine-100e_s3dis-seg_test-area4.py │ ├── dgcnn_4xb32-cosine-100e_s3dis-seg_test-area5.py │ ├── dgcnn_4xb32-cosine-100e_s3dis-seg_test-area6.py │ └── metafile.yml ├── dynamic_voxelization │ ├── README.md │ ├── metafile.yml │ ├── pointpillars_dv_secfpn_8xb6-160e_kitti-3d-car.py │ ├── second_dv_secfpn_8xb2-cosine-80e_kitti-3d-3class.py │ └── second_dv_secfpn_8xb6-80e_kitti-3d-car.py ├── fcaf3d │ ├── README.md │ ├── fcaf3d_2xb8_s3dis-3d-5class.py │ ├── fcaf3d_2xb8_scannet-3d-18class.py │ ├── fcaf3d_2xb8_sunrgbd-3d-10class.py │ └── metafile.yml ├── fcos3d │ ├── README.md │ ├── fcos3d_r101-caffe-dcn_fpn_head-gn_8xb2-1x_nus-mono3d.py │ ├── fcos3d_r101-caffe-dcn_fpn_head-gn_8xb2-1x_nus-mono3d_finetune.py │ └── metafile.yml ├── free_anchor │ ├── README.md │ ├── metafile.yml │ ├── pointpillars_hv_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d.py │ ├── pointpillars_hv_regnet-1.6gf_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d.py │ ├── pointpillars_hv_regnet-1.6gf_fpn_head-free-anchor_sbn-all_8xb4-strong-aug-3x_nus-3d.py │ ├── pointpillars_hv_regnet-3.2gf_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d.py │ ├── pointpillars_hv_regnet-3.2gf_fpn_head-free-anchor_sbn-all_8xb4-strong-aug-3x_nus-3d.py │ └── pointpillars_hv_regnet-400mf_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d.py ├── groupfree3d │ ├── README.md │ ├── groupfree3d_head-L12-O256_4xb8_scannet-seg.py │ ├── groupfree3d_head-L6-O256_4xb8_scannet-seg.py │ ├── groupfree3d_w2x-head-L12-O256_4xb8_scannet-seg.py │ ├── groupfree3d_w2x-head-L12-O512_4xb8_scannet-seg.py │ └── metafile.yml ├── h3dnet │ ├── README.md │ ├── h3dnet_8xb3_scannet-seg.py │ └── metafile.yml ├── imvotenet │ ├── README.md │ ├── imvotenet_faster-rcnn-r50_fpn_4xb2_sunrgbd-3d.py │ ├── imvotenet_stage2_8xb16_sunrgbd-3d.py │ └── metafile.yml ├── imvoxelnet │ ├── README.md │ ├── imvoxelnet_2xb4_sunrgbd-3d-10class.py │ ├── imvoxelnet_8xb4_kitti-3d-car.py │ └── metafile.yml ├── minkunet │ ├── README.md │ ├── metafile.yml │ ├── minkunet18_w16_torchsparse_8xb2-amp-15e_semantickitti.py │ ├── minkunet18_w20_torchsparse_8xb2-amp-15e_semantickitti.py │ ├── minkunet18_w32_torchsparse_8xb2-amp-15e_semantickitti.py │ ├── minkunet34_w32_minkowski_8xb2-laser-polar-mix-3x_semantickitti.py │ ├── minkunet34_w32_spconv_8xb2-amp-laser-polar-mix-3x_semantickitti.py │ ├── minkunet34_w32_spconv_8xb2-laser-polar-mix-3x_semantickitti.py │ ├── minkunet34_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti.py │ ├── minkunet34_w32_torchsparse_8xb2-laser-polar-mix-3x_semantickitti.py │ └── minkunet34v2_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti.py ├── monoflex │ ├── README.md │ └── metafile.yml ├── mvfcos3d │ ├── README.md │ ├── multiview-fcos3d_r101-dcn_8xb2_waymoD5-3d-3class.py │ └── multiview-fcos3d_r101-dcn_centerhead_16xb2_waymoD5-3d-3class.py ├── mvxnet │ ├── README.md │ ├── metafile.yml │ └── mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class.py ├── nuimages │ ├── README.md │ ├── cascade-mask-rcnn-r50-fpn_coco-20e_nuim.py │ ├── cascade-mask-rcnn_r101_fpn_1x_nuim.py │ ├── cascade-mask-rcnn_r50_fpn_1x_nuim.py │ ├── cascade-mask-rcnn_r50_fpn_coco-20e-1x_nuim.py │ ├── cascade-mask-rcnn_x101_32x4d_fpn_1x_nuim.py │ ├── htc_r50_fpn_1x_nuim.py │ ├── htc_r50_fpn_coco-20e-1x_nuim.py │ ├── htc_r50_fpn_coco-20e_nuim.py │ ├── htc_r50_fpn_head-without-semantic_1x_nuim.py │ ├── htc_x101_64x4d_fpn_dconv_c3-c5_coco-20e-1xb16_nuim.py │ ├── mask-rcnn_r101_fpn_1x_nuim.py │ ├── mask-rcnn_r50_caffe_fpn_1x_nuim.py │ ├── mask-rcnn_r50_caffe_fpn_coco-3x_1x_nuim.py │ ├── mask-rcnn_r50_caffe_fpn_coco-3x_20e_nuim.py │ ├── mask-rcnn_r50_fpn_1x_nuim.py │ ├── mask-rcnn_r50_fpn_coco-2x_1x_nuim.py │ ├── mask-rcnn_r50_fpn_coco-2x_1x_nus-2d.py │ ├── mask-rcnn_x101_32x4d_fpn_1x_nuim.py │ └── metafile.yml ├── paconv │ ├── README.md │ ├── metafile.yml │ ├── paconv_ssg-cuda_8xb8-cosine-200e_s3dis-seg.py │ └── paconv_ssg_8xb8-cosine-150e_s3dis-seg.py ├── parta2 │ ├── README.md │ ├── metafile.yml │ ├── parta2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py │ └── parta2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-car.py ├── pgd │ ├── README.md │ ├── metafile.yml │ ├── pgd_r101-caffe_fpn_head-gn_16xb2-1x_nus-mono3d.py │ ├── pgd_r101-caffe_fpn_head-gn_16xb2-1x_nus-mono3d_finetune.py │ ├── pgd_r101-caffe_fpn_head-gn_16xb2-2x_nus-mono3d.py │ ├── pgd_r101-caffe_fpn_head-gn_16xb2-2x_nus-mono3d_finetune.py │ ├── pgd_r101-caffe_fpn_head-gn_4xb3-4x_kitti-mono3d.py │ ├── pgd_r101_fpn-head_dcn_16xb3_waymoD5-fov-mono3d.py │ ├── pgd_r101_fpn-head_dcn_16xb3_waymoD5-mv-mono3d.py │ ├── pgd_r101_fpn_gn-head_dcn_8xb3-2x_waymoD3-fov-mono3d.py │ └── pgd_r101_fpn_gn-head_dcn_8xb3-2x_waymoD3-mv-mono3d.py ├── point_rcnn │ ├── README.md │ ├── metafile.yml │ └── point-rcnn_8xb2_kitti-3d-3class.py ├── pointnet2 │ ├── README.md │ ├── metafile.yml │ ├── pointnet2_msg_2xb16-cosine-250e_scannet-seg-xyz-only.py │ ├── pointnet2_msg_2xb16-cosine-250e_scannet-seg.py │ ├── pointnet2_msg_2xb16-cosine-80e_s3dis-seg.py │ ├── pointnet2_ssg_2xb16-cosine-200e_scannet-seg-xyz-only.py │ ├── pointnet2_ssg_2xb16-cosine-200e_scannet-seg.py │ └── pointnet2_ssg_2xb16-cosine-50e_s3dis-seg.py ├── pointpillars │ ├── README.md │ ├── metafile.yml │ ├── pointpillars_hv_fpn_sbn-all_8xb2-2x_lyft-3d-range100.py │ ├── pointpillars_hv_fpn_sbn-all_8xb2-2x_lyft-3d.py │ ├── pointpillars_hv_fpn_sbn-all_8xb2-amp-2x_nus-3d.py │ ├── pointpillars_hv_fpn_sbn-all_8xb4-2x_nus-3d.py │ ├── pointpillars_hv_secfpn_8xb6-160e_kitti-3d-3class.py │ ├── pointpillars_hv_secfpn_8xb6-160e_kitti-3d-car.py │ ├── pointpillars_hv_secfpn_sbn-all_16xb2-2x_waymo-3d-3class.py │ ├── pointpillars_hv_secfpn_sbn-all_16xb2-2x_waymo-3d-car.py │ ├── pointpillars_hv_secfpn_sbn-all_16xb2-2x_waymoD5-3d-3class.py │ ├── pointpillars_hv_secfpn_sbn-all_16xb2-2x_waymoD5-3d-car.py │ ├── pointpillars_hv_secfpn_sbn-all_8xb2-2x_lyft-3d-range100.py │ ├── pointpillars_hv_secfpn_sbn-all_8xb2-2x_lyft-3d.py │ ├── pointpillars_hv_secfpn_sbn-all_8xb2-amp-2x_nus-3d.py │ └── pointpillars_hv_secfpn_sbn-all_8xb4-2x_nus-3d.py ├── pv_rcnn │ ├── README.md │ ├── metafile.yml │ └── pv_rcnn_8xb2-80e_kitti-3d-3class.py ├── regnet │ ├── README.md │ ├── metafile.yml │ ├── pointpillars_hv_regnet-1.6gf_fpn_sbn-all_8xb4-2x_nus-3d.py │ ├── pointpillars_hv_regnet-400mf_fpn_sbn-all_8xb2-2x_lyft-3d.py │ ├── pointpillars_hv_regnet-400mf_fpn_sbn-all_8xb4-2x_nus-3d.py │ ├── pointpillars_hv_regnet-400mf_fpn_sbn-all_range100_8xb2-2x_lyft-3d.py │ ├── pointpillars_hv_regnet-400mf_secfpn_sbn-all_8xb2-2x_lyft-3d.py │ ├── pointpillars_hv_regnet-400mf_secfpn_sbn-all_8xb4-2x_nus-3d.py │ └── pointpillars_hv_regnet-400mf_secfpn_sbn-all_range100_8xb2-2x_lyft-3d.py ├── sassd │ ├── README.md │ └── sassd_8xb6-80e_kitti-3d-3class.py ├── second │ ├── README.md │ ├── metafile.yml │ ├── second_hv_secfpn_8xb6-80e_kitti-3d-3class.py │ ├── second_hv_secfpn_8xb6-80e_kitti-3d-car.py │ ├── second_hv_secfpn_8xb6-amp-80e_kitti-3d-3class.py │ ├── second_hv_secfpn_8xb6-amp-80e_kitti-3d-car.py │ └── second_hv_secfpn_sbn-all_16xb2-2x_waymoD5-3d-3class.py ├── smoke │ ├── README.md │ ├── metafile.yml │ └── smoke_dla34_dlaneck_gn-all_4xb8-6x_kitti-mono3d.py ├── spvcnn │ ├── README.md │ ├── metafile.yml │ ├── spvcnn_w16_8xb2-amp-15e_semantickitti.py │ ├── spvcnn_w20_8xb2-amp-15e_semantickitti.py │ ├── spvcnn_w32_8xb2-amp-15e_semantickitti.py │ └── spvcnn_w32_8xb2-amp-laser-polar-mix-3x_semantickitti.py ├── ssn │ ├── README.md │ ├── metafile.yml │ ├── ssn_hv_regnet-400mf_secfpn_sbn-all_16xb1-2x_lyft-3d.py │ ├── ssn_hv_regnet-400mf_secfpn_sbn-all_16xb2-2x_nus-3d.py │ ├── ssn_hv_secfpn_sbn-all_16xb2-2x_lyft-3d.py │ └── ssn_hv_secfpn_sbn-all_16xb2-2x_nus-3d.py └── votenet │ ├── README.md │ ├── metafile.yml │ ├── votenet_8xb16_sunrgbd-3d.py │ ├── votenet_8xb8_scannet-3d.py │ └── votenet_head-iouloss_8xb8_scannet-3d.py ├── data ├── lyft │ ├── test.txt │ ├── train.txt │ └── val.txt ├── s3dis │ ├── README.md │ ├── collect_indoor3d_data.py │ ├── indoor3d_util.py │ └── meta_data │ │ ├── anno_paths.txt │ │ └── class_names.txt ├── scannet │ ├── README.md │ ├── batch_load_scannet_data.py │ ├── extract_posed_images.py │ ├── load_scannet_data.py │ ├── meta_data │ │ ├── scannet_means.npz │ │ ├── scannet_train.txt │ │ ├── scannetv2-labels.combined.tsv │ │ ├── scannetv2_test.txt │ │ ├── scannetv2_train.txt │ │ └── scannetv2_val.txt │ └── scannet_utils.py └── sunrgbd │ ├── README.md │ └── matlab │ ├── extract_rgbd_data_v1.m │ ├── extract_rgbd_data_v2.m │ └── extract_split.m ├── dataset-index.yml ├── demo ├── data │ ├── kitti │ │ ├── 000008.bin │ │ ├── 000008.pkl │ │ ├── 000008.png │ │ └── 000008.txt │ ├── nuscenes │ │ ├── n015-2018-07-24-11-22-45+0800.pkl │ │ ├── n015-2018-07-24-11-22-45+0800__CAM_BACK_LEFT__1532402927647423.jpg │ │ ├── n015-2018-07-24-11-22-45+0800__CAM_BACK_RIGHT__1532402927627893.jpg │ │ ├── n015-2018-07-24-11-22-45+0800__CAM_BACK__1532402927637525.jpg │ │ ├── n015-2018-07-24-11-22-45+0800__CAM_FRONT_LEFT__1532402927604844.jpg │ │ ├── n015-2018-07-24-11-22-45+0800__CAM_FRONT_RIGHT__1532402927620339.jpg │ │ ├── n015-2018-07-24-11-22-45+0800__CAM_FRONT__1532402927612460.jpg │ │ └── n015-2018-07-24-11-22-45+0800__LIDAR_TOP__1532402927647951.pcd.bin │ ├── scannet │ │ └── scene0000_00.bin │ └── sunrgbd │ │ ├── 000017.bin │ │ ├── 000017.jpg │ │ └── sunrgbd_000017_infos.pkl ├── inference_demo.ipynb ├── mono_det_demo.py ├── multi_modality_demo.py ├── pcd_demo.py └── pcd_seg_demo.py ├── docker ├── Dockerfile └── serve │ ├── Dockerfile │ ├── config.properties │ └── entrypoint.sh ├── docs ├── en │ ├── Makefile │ ├── _static │ │ ├── css │ │ │ └── readthedocs.css │ │ └── image │ │ │ └── mmdet3d-logo.png │ ├── advanced_guides │ │ ├── customize_dataset.md │ │ ├── customize_models.md │ │ ├── customize_runtime.md │ │ ├── datasets │ │ │ ├── index.rst │ │ │ ├── kitti.md │ │ │ ├── lyft.md │ │ │ ├── nuscenes.md │ │ │ ├── s3dis.md │ │ │ ├── scannet.md │ │ │ ├── semantickitti.md │ │ │ ├── sunrgbd.md │ │ │ └── waymo.md │ │ ├── index.rst │ │ ├── pure_point_cloud_dataset.md │ │ └── supported_tasks │ │ │ ├── index.rst │ │ │ ├── lidar_det3d.md │ │ │ ├── lidar_sem_seg3d.md │ │ │ └── vision_det3d.md │ ├── api.rst │ ├── conf.py │ ├── get_started.md │ ├── index.rst │ ├── make.bat │ ├── migration.md │ ├── model_zoo.md │ ├── notes │ │ ├── benchmarks.md │ │ ├── changelog.md │ │ ├── changelog_v1.0.x.md │ │ ├── compatibility.md │ │ ├── contribution_guides.md │ │ ├── faq.md │ │ └── index.rst │ ├── stat.py │ ├── switch_language.md │ └── user_guides │ │ ├── backends_support.md │ │ ├── config.md │ │ ├── coord_sys_tutorial.md │ │ ├── data_pipeline.md │ │ ├── dataset_prepare.md │ │ ├── index.rst │ │ ├── inference.md │ │ ├── model_deployment.md │ │ ├── new_data_model.md │ │ ├── train_test.md │ │ ├── useful_tools.md │ │ └── visualization.md └── zh_cn │ ├── Makefile │ ├── _static │ ├── css │ │ └── readthedocs.css │ └── image │ │ └── mmdet3d-logo.png │ ├── advanced_guides │ ├── customize_dataset.md │ ├── customize_models.md │ ├── customize_runtime.md │ ├── datasets │ │ ├── index.rst │ │ ├── kitti.md │ │ ├── lyft.md │ │ ├── nuscenes.md │ │ ├── s3dis.md │ │ ├── scannet.md │ │ ├── semantickitti.md │ │ ├── sunrgbd.md │ │ └── waymo.md │ ├── index.rst │ └── supported_tasks │ │ ├── index.rst │ │ ├── lidar_det3d.md │ │ ├── lidar_sem_seg3d.md │ │ └── vision_det3d.md │ ├── api.rst │ ├── conf.py │ ├── get_started.md │ ├── index.rst │ ├── make.bat │ ├── model_zoo.md │ ├── notes │ ├── benchmarks.md │ ├── changelog.md │ ├── changelog_v1.0.x.md │ ├── compatibility.md │ ├── faq.md │ └── index.rst │ ├── stat.py │ ├── switch_language.md │ └── user_guides │ ├── backends_support.md │ ├── config.md │ ├── coord_sys_tutorial.md │ ├── data_pipeline.md │ ├── dataset_prepare.md │ ├── index.rst │ ├── inference.md │ ├── model_deployment.md │ ├── new_data_model.md │ ├── train_test.md │ ├── useful_tools.md │ └── visualization.md ├── mmdet3d ├── __init__.py ├── apis │ ├── __init__.py │ ├── inference.py │ └── inferencers │ │ ├── __init__.py │ │ ├── base_3d_inferencer.py │ │ ├── lidar_det3d_inferencer.py │ │ ├── lidar_seg3d_inferencer.py │ │ ├── mono_det3d_inferencer.py │ │ └── multi_modality_det3d_inferencer.py ├── configs │ ├── _base_ │ │ ├── datasets │ │ │ ├── kitti_3d_3class.py │ │ │ ├── kitti_3d_car.py │ │ │ ├── kitti_mono3d.py │ │ │ ├── lyft_3d.py │ │ │ ├── lyft_3d_range100.py │ │ │ ├── nuim_instance.py │ │ │ ├── nus_3d.py │ │ │ ├── nus_mono3d.py │ │ │ ├── s3dis_3d.py │ │ │ ├── s3dis_seg.py │ │ │ ├── scannet_3d.py │ │ │ ├── scannet_seg.py │ │ │ ├── semantickitti.py │ │ │ ├── sunrgbd_3d.py │ │ │ ├── waymoD5_3d_3class.py │ │ │ ├── waymoD5_3d_car.py │ │ │ ├── waymoD5_fov_mono3d_3class.py │ │ │ ├── waymoD5_mv3d_3class.py │ │ │ └── waymoD5_mv_mono3d_3class.py │ │ ├── default_runtime.py │ │ ├── models │ │ │ ├── centerpoint_pillar02_second_secfpn_nus.py │ │ │ ├── centerpoint_voxel01_second_secfpn_nus.py │ │ │ ├── cylinder3d.py │ │ │ ├── fcos3d.py │ │ │ ├── minkunet.py │ │ │ ├── pgd.py │ │ │ └── votenet.py │ │ └── schedules │ │ │ ├── cosine.py │ │ │ ├── cyclic_20e.py │ │ │ ├── cyclic_40e.py │ │ │ ├── mmdet_schedule_1x.py │ │ │ ├── schedule_2x.py │ │ │ ├── schedule_3x.py │ │ │ ├── seg_cosine_100e.py │ │ │ ├── seg_cosine_150e.py │ │ │ ├── seg_cosine_200e.py │ │ │ └── seg_cosine_50e.py │ ├── centerpoint │ │ ├── centerpoint_pillar02_second_secfpn_8xb4_cyclic_20e_nus_3d.py │ │ └── centerpoint_voxel01_second_secfpn_8xb4_cyclic_20e_nus_3d.py │ ├── cylinder3d │ │ ├── cylinder3d_4xb4-3x_semantickitti.py │ │ └── cylinder3d_8xb2-laser-polar-mix-3x_semantickitti.py │ ├── minkunet │ │ └── minkunet34_w32_torchsparse_8xb2_laser_polar_mix_3x_semantickitti.py │ ├── mvxnet │ │ └── mvxnet_fpn_dv_second_secfpn_8xb2_80e_kitti_3d_3class.py │ ├── pgd │ │ └── pgd_r101_caffe_fpn_head_gn_4xb3_4x_kitti_mono3d.py │ └── votenet │ │ ├── __init__.py │ │ └── votenet_8xb8_scannet_3d.py ├── datasets │ ├── __init__.py │ ├── convert_utils.py │ ├── dataset_wrappers.py │ ├── det3d_dataset.py │ ├── kitti2d_dataset.py │ ├── kitti_dataset.py │ ├── lyft_dataset.py │ ├── nuscenes_dataset.py │ ├── s3dis_dataset.py │ ├── scannet_dataset.py │ ├── seg3d_dataset.py │ ├── semantickitti_dataset.py │ ├── sunrgbd_dataset.py │ ├── transforms │ │ ├── __init__.py │ │ ├── data_augment_utils.py │ │ ├── dbsampler.py │ │ ├── formating.py │ │ ├── loading.py │ │ ├── test_time_aug.py │ │ └── transforms_3d.py │ ├── utils.py │ └── waymo_dataset.py ├── engine │ ├── __init__.py │ └── hooks │ │ ├── __init__.py │ │ ├── benchmark_hook.py │ │ ├── disable_object_sample_hook.py │ │ └── visualization_hook.py ├── evaluation │ ├── __init__.py │ ├── functional │ │ ├── __init__.py │ │ ├── indoor_eval.py │ │ ├── instance_seg_eval.py │ │ ├── kitti_utils │ │ │ ├── __init__.py │ │ │ ├── eval.py │ │ │ └── rotate_iou.py │ │ ├── lyft_eval.py │ │ ├── panoptic_seg_eval.py │ │ ├── scannet_utils │ │ │ ├── __init__.py │ │ │ ├── evaluate_semantic_instance.py │ │ │ └── util_3d.py │ │ ├── seg_eval.py │ │ └── waymo_utils │ │ │ ├── __init__.py │ │ │ └── prediction_to_waymo.py │ └── metrics │ │ ├── __init__.py │ │ ├── indoor_metric.py │ │ ├── instance_seg_metric.py │ │ ├── kitti_metric.py │ │ ├── lyft_metric.py │ │ ├── nuscenes_metric.py │ │ ├── panoptic_seg_metric.py │ │ ├── seg_metric.py │ │ └── waymo_metric.py ├── models │ ├── __init__.py │ ├── backbones │ │ ├── __init__.py │ │ ├── base_pointnet.py │ │ ├── cylinder3d.py │ │ ├── dgcnn.py │ │ ├── dla.py │ │ ├── mink_resnet.py │ │ ├── minkunet_backbone.py │ │ ├── multi_backbone.py │ │ ├── nostem_regnet.py │ │ ├── pointnet2_sa_msg.py │ │ ├── pointnet2_sa_ssg.py │ │ ├── second.py │ │ └── spvcnn_backone.py │ ├── data_preprocessors │ │ ├── __init__.py │ │ ├── data_preprocessor.py │ │ ├── utils.py │ │ └── voxelize.py │ ├── decode_heads │ │ ├── __init__.py │ │ ├── cylinder3d_head.py │ │ ├── decode_head.py │ │ ├── dgcnn_head.py │ │ ├── minkunet_head.py │ │ ├── paconv_head.py │ │ └── pointnet2_head.py │ ├── dense_heads │ │ ├── __init__.py │ │ ├── anchor3d_head.py │ │ ├── anchor_free_mono3d_head.py │ │ ├── base_3d_dense_head.py │ │ ├── base_conv_bbox_head.py │ │ ├── base_mono3d_dense_head.py │ │ ├── centerpoint_head.py │ │ ├── fcaf3d_head.py │ │ ├── fcos_mono3d_head.py │ │ ├── free_anchor3d_head.py │ │ ├── groupfree3d_head.py │ │ ├── imvoxel_head.py │ │ ├── monoflex_head.py │ │ ├── parta2_rpn_head.py │ │ ├── pgd_head.py │ │ ├── point_rpn_head.py │ │ ├── shape_aware_head.py │ │ ├── smoke_mono3d_head.py │ │ ├── ssd_3d_head.py │ │ ├── train_mixins.py │ │ └── vote_head.py │ ├── detectors │ │ ├── __init__.py │ │ ├── base.py │ │ ├── centerpoint.py │ │ ├── dfm.py │ │ ├── dynamic_voxelnet.py │ │ ├── fcos_mono3d.py │ │ ├── groupfree3dnet.py │ │ ├── h3dnet.py │ │ ├── imvotenet.py │ │ ├── imvoxelnet.py │ │ ├── mink_single_stage.py │ │ ├── multiview_dfm.py │ │ ├── mvx_faster_rcnn.py │ │ ├── mvx_two_stage.py │ │ ├── parta2.py │ │ ├── point_rcnn.py │ │ ├── pv_rcnn.py │ │ ├── sassd.py │ │ ├── single_stage.py │ │ ├── single_stage_mono3d.py │ │ ├── smoke_mono3d.py │ │ ├── ssd3dnet.py │ │ ├── two_stage.py │ │ ├── votenet.py │ │ └── voxelnet.py │ ├── layers │ │ ├── __init__.py │ │ ├── box3d_nms.py │ │ ├── dgcnn_modules │ │ │ ├── __init__.py │ │ │ ├── dgcnn_fa_module.py │ │ │ ├── dgcnn_fp_module.py │ │ │ └── dgcnn_gf_module.py │ │ ├── edge_fusion_module.py │ │ ├── fusion_layers │ │ │ ├── __init__.py │ │ │ ├── coord_transform.py │ │ │ ├── point_fusion.py │ │ │ └── vote_fusion.py │ │ ├── minkowski_engine_block.py │ │ ├── mlp.py │ │ ├── norm.py │ │ ├── paconv │ │ │ ├── __init__.py │ │ │ ├── paconv.py │ │ │ └── utils.py │ │ ├── pointnet_modules │ │ │ ├── __init__.py │ │ │ ├── builder.py │ │ │ ├── paconv_sa_module.py │ │ │ ├── point_fp_module.py │ │ │ ├── point_sa_module.py │ │ │ └── stack_point_sa_module.py │ │ ├── sparse_block.py │ │ ├── spconv │ │ │ ├── __init__.py │ │ │ └── overwrite_spconv │ │ │ │ ├── __init__.py │ │ │ │ └── write_spconv2.py │ │ ├── torchsparse │ │ │ ├── __init__.py │ │ │ └── torchsparse_wrapper.py │ │ ├── torchsparse_block.py │ │ ├── transformer.py │ │ └── vote_module.py │ ├── losses │ │ ├── __init__.py │ │ ├── axis_aligned_iou_loss.py │ │ ├── chamfer_distance.py │ │ ├── lovasz_loss.py │ │ ├── multibin_loss.py │ │ ├── paconv_regularization_loss.py │ │ ├── rotated_iou_loss.py │ │ └── uncertain_smooth_l1_loss.py │ ├── middle_encoders │ │ ├── __init__.py │ │ ├── pillar_scatter.py │ │ ├── sparse_encoder.py │ │ ├── sparse_unet.py │ │ └── voxel_set_abstraction.py │ ├── necks │ │ ├── __init__.py │ │ ├── dla_neck.py │ │ ├── imvoxel_neck.py │ │ ├── pointnet2_fp_neck.py │ │ └── second_fpn.py │ ├── roi_heads │ │ ├── __init__.py │ │ ├── base_3droi_head.py │ │ ├── bbox_heads │ │ │ ├── __init__.py │ │ │ ├── h3d_bbox_head.py │ │ │ ├── parta2_bbox_head.py │ │ │ ├── point_rcnn_bbox_head.py │ │ │ └── pv_rcnn_bbox_head.py │ │ ├── h3d_roi_head.py │ │ ├── mask_heads │ │ │ ├── __init__.py │ │ │ ├── foreground_segmentation_head.py │ │ │ ├── pointwise_semantic_head.py │ │ │ └── primitive_head.py │ │ ├── part_aggregation_roi_head.py │ │ ├── point_rcnn_roi_head.py │ │ ├── pv_rcnn_roi_head.py │ │ └── roi_extractors │ │ │ ├── __init__.py │ │ │ ├── batch_roigridpoint_extractor.py │ │ │ ├── single_roiaware_extractor.py │ │ │ └── single_roipoint_extractor.py │ ├── segmentors │ │ ├── __init__.py │ │ ├── base.py │ │ ├── cylinder3d.py │ │ ├── encoder_decoder.py │ │ ├── minkunet.py │ │ └── seg3d_tta.py │ ├── task_modules │ │ ├── __init__.py │ │ ├── anchor │ │ │ ├── __init__.py │ │ │ ├── anchor_3d_generator.py │ │ │ └── builder.py │ │ ├── assigners │ │ │ ├── __init__.py │ │ │ └── max_3d_iou_assigner.py │ │ ├── builder.py │ │ ├── coders │ │ │ ├── __init__.py │ │ │ ├── anchor_free_bbox_coder.py │ │ │ ├── centerpoint_bbox_coders.py │ │ │ ├── delta_xyzwhlr_bbox_coder.py │ │ │ ├── fcos3d_bbox_coder.py │ │ │ ├── groupfree3d_bbox_coder.py │ │ │ ├── monoflex_bbox_coder.py │ │ │ ├── partial_bin_based_bbox_coder.py │ │ │ ├── pgd_bbox_coder.py │ │ │ ├── point_xyzwhlr_bbox_coder.py │ │ │ └── smoke_bbox_coder.py │ │ ├── samplers │ │ │ ├── __init__.py │ │ │ ├── iou_neg_piecewise_sampler.py │ │ │ └── pseudosample.py │ │ └── voxel │ │ │ ├── __init__.py │ │ │ └── voxel_generator.py │ ├── test_time_augs │ │ ├── __init__.py │ │ └── merge_augs.py │ ├── utils │ │ ├── __init__.py │ │ ├── add_prefix.py │ │ ├── clip_sigmoid.py │ │ ├── edge_indices.py │ │ ├── gaussian.py │ │ ├── gen_keypoints.py │ │ └── handle_objs.py │ └── voxel_encoders │ │ ├── __init__.py │ │ ├── pillar_encoder.py │ │ ├── utils.py │ │ └── voxel_encoder.py ├── registry.py ├── structures │ ├── __init__.py │ ├── bbox_3d │ │ ├── __init__.py │ │ ├── base_box3d.py │ │ ├── box_3d_mode.py │ │ ├── cam_box3d.py │ │ ├── coord_3d_mode.py │ │ ├── depth_box3d.py │ │ ├── lidar_box3d.py │ │ └── utils.py │ ├── det3d_data_sample.py │ ├── ops │ │ ├── __init__.py │ │ ├── box_np_ops.py │ │ ├── iou3d_calculator.py │ │ └── transforms.py │ ├── point_data.py │ └── points │ │ ├── __init__.py │ │ ├── base_points.py │ │ ├── cam_points.py │ │ ├── depth_points.py │ │ └── lidar_points.py ├── testing │ ├── __init__.py │ ├── data_utils.py │ └── model_utils.py ├── utils │ ├── __init__.py │ ├── array_converter.py │ ├── collect_env.py │ ├── compat_cfg.py │ ├── misc.py │ ├── setup_env.py │ └── typing_utils.py ├── version.py └── visualization │ ├── __init__.py │ ├── local_visualizer.py │ └── vis_utils.py ├── model-index.yml ├── projects ├── BEVFusion │ ├── README.md │ ├── bevfusion │ │ ├── __init__.py │ │ ├── bevfusion.py │ │ ├── bevfusion_necks.py │ │ ├── depth_lss.py │ │ ├── loading.py │ │ ├── ops │ │ │ ├── __init__.py │ │ │ ├── bev_pool │ │ │ │ ├── __init__.py │ │ │ │ ├── bev_pool.py │ │ │ │ └── src │ │ │ │ │ ├── bev_pool.cpp │ │ │ │ │ └── bev_pool_cuda.cu │ │ │ └── voxel │ │ │ │ ├── __init__.py │ │ │ │ ├── scatter_points.py │ │ │ │ ├── src │ │ │ │ ├── scatter_points_cpu.cpp │ │ │ │ ├── scatter_points_cuda.cu │ │ │ │ ├── voxelization.cpp │ │ │ │ ├── voxelization.h │ │ │ │ ├── voxelization_cpu.cpp │ │ │ │ └── voxelization_cuda.cu │ │ │ │ └── voxelize.py │ │ ├── sparse_encoder.py │ │ ├── transformer.py │ │ ├── transforms_3d.py │ │ ├── transfusion_head.py │ │ └── utils.py │ ├── configs │ │ ├── bevfusion_lidar-cam_voxel0075_second_secfpn_8xb4-cyclic-20e_nus-3d.py │ │ └── bevfusion_lidar_voxel0075_second_secfpn_8xb4-cyclic-20e_nus-3d.py │ ├── demo │ │ └── multi_modality_demo.py │ └── setup.py ├── CENet │ ├── README.md │ ├── cenet │ │ ├── __init__.py │ │ ├── boundary_loss.py │ │ ├── cenet_backbone.py │ │ ├── range_image_head.py │ │ ├── range_image_segmentor.py │ │ ├── transforms_3d.py │ │ └── utils.py │ └── configs │ │ ├── cenet-64x1024_4xb4_semantickitti.py │ │ ├── cenet-64x2048_4xb4_semantickitti.py │ │ └── cenet-64x512_4xb4_semantickitti.py ├── CenterFormer │ ├── README.md │ ├── centerformer │ │ ├── __init__.py │ │ ├── bbox_ops.py │ │ ├── centerformer.py │ │ ├── centerformer_backbone.py │ │ ├── centerformer_head.py │ │ ├── losses.py │ │ ├── multi_scale_deform_attn.py │ │ └── transformer.py │ └── configs │ │ └── centerformer_voxel01_second-attn_secfpn-attn_4xb4-cyclic-20e_waymoD5-3d-3class.py ├── DETR3D │ ├── README.md │ ├── configs │ │ ├── detr3d_r101_gridmask.py │ │ ├── detr3d_r101_gridmask_cbgs.py │ │ └── detr3d_vovnet_gridmask_trainval_cbgs.py │ ├── detr3d │ │ ├── __init__.py │ │ ├── detr3d.py │ │ ├── detr3d_head.py │ │ ├── detr3d_transformer.py │ │ ├── grid_mask.py │ │ ├── hungarian_assigner_3d.py │ │ ├── match_cost.py │ │ ├── nms_free_coder.py │ │ ├── util.py │ │ └── vovnet.py │ └── old_detr3d_converter.py ├── DSVT │ ├── README.md │ ├── configs │ │ └── dsvt_voxel032_res-second_secfpn_8xb1-cyclic-12e_waymoD5-3d-3class.py │ ├── dsvt │ │ ├── __init__.py │ │ ├── disable_aug_hook.py │ │ ├── dsvt.py │ │ ├── dsvt_head.py │ │ ├── dsvt_input_layer.py │ │ ├── dsvt_transformer.py │ │ ├── dynamic_pillar_vfe.py │ │ ├── map2bev.py │ │ ├── ops │ │ │ └── ingroup_inds │ │ │ │ ├── ingroup_inds_op.py │ │ │ │ └── src │ │ │ │ ├── error.cuh │ │ │ │ ├── ingroup_inds.cpp │ │ │ │ └── ingroup_inds_kernel.cu │ │ ├── res_second.py │ │ ├── transforms_3d.py │ │ └── utils.py │ └── setup.py ├── NeRF-Det │ ├── README.md │ ├── configs │ │ ├── nerfdet_res101_2x_low_res_depth.py │ │ ├── nerfdet_res50_2x_low_res.py │ │ └── nerfdet_res50_2x_low_res_depth.py │ ├── nerfdet │ │ ├── __init__.py │ │ ├── data_preprocessor.py │ │ ├── formating.py │ │ ├── multiview_pipeline.py │ │ ├── nerf_det3d_data_sample.py │ │ ├── nerf_utils │ │ │ ├── nerf_mlp.py │ │ │ ├── projection.py │ │ │ ├── render_ray.py │ │ │ └── save_rendered_img.py │ │ ├── nerfdet.py │ │ ├── nerfdet_head.py │ │ └── scannet_multiview_dataset.py │ └── prepare_infos.py ├── PETR │ ├── README.md │ ├── configs │ │ └── petr_vovnet_gridmask_p4_800x320.py │ └── petr │ │ ├── __init__.py │ │ ├── cp_fpn.py │ │ ├── grid_mask.py │ │ ├── hungarian_assigner_3d.py │ │ ├── match_cost.py │ │ ├── nms_free_coder.py │ │ ├── petr.py │ │ ├── petr_head.py │ │ ├── petr_transformer.py │ │ ├── positional_encoding.py │ │ ├── transforms_3d.py │ │ ├── utils.py │ │ └── vovnetcp.py ├── TPVFormer │ ├── README.md │ ├── configs │ │ └── tpvformer_8xb1-2x_nus-seg.py │ └── tpvformer │ │ ├── __init__.py │ │ ├── cross_view_hybrid_attention.py │ │ ├── data_preprocessor.py │ │ ├── image_cross_attention.py │ │ ├── loading.py │ │ ├── nuscenes_dataset.py │ │ ├── positional_encoding.py │ │ ├── tpvformer.py │ │ ├── tpvformer_encoder.py │ │ ├── tpvformer_head.py │ │ └── tpvformer_layer.py ├── TR3D │ ├── README.md │ ├── configs │ │ ├── tr3d.py │ │ ├── tr3d_1xb16_s3dis-3d-5class.py │ │ ├── tr3d_1xb16_scannet-3d-18class.py │ │ └── tr3d_1xb16_sunrgbd-3d-10class.py │ └── tr3d │ │ ├── __init__.py │ │ ├── axis_aligned_iou_loss.py │ │ ├── mink_resnet.py │ │ ├── rotated_iou_loss.py │ │ ├── tr3d_head.py │ │ ├── tr3d_neck.py │ │ └── transforms_3d.py └── example_project │ ├── README.md │ ├── configs │ └── fcos3d_dummy-resnet-caffe-dcn_fpn_head-gn_8xb2-1x_nus-mono3d.py │ └── dummy │ ├── __init__.py │ └── dummy_resnet.py ├── requirements.txt ├── requirements ├── build.txt ├── docs.txt ├── mminstall.txt ├── optional.txt ├── readthedocs.txt ├── runtime.txt └── tests.txt ├── resources ├── browse_dataset_mono.png ├── browse_dataset_multi_modality.png ├── browse_dataset_seg.png ├── coord_sys_all.png ├── data_pipeline.png ├── loss_curve.png ├── mmdet3d-logo.png ├── mmdet3d_outdoor_demo.gif ├── nuimages_demo.gif ├── open3d_visual.gif └── open3d_visual.png ├── setup.cfg ├── setup.py ├── tests ├── data │ ├── kitti │ │ ├── a.bin │ │ ├── kitti_dbinfos_train.pkl │ │ ├── kitti_gt_database │ │ │ └── 0_Pedestrian_0.bin │ │ ├── kitti_infos_mono3d.coco.json │ │ ├── kitti_infos_mono3d.pkl │ │ ├── kitti_infos_train.pkl │ │ ├── mono3d_sample_results.pkl │ │ ├── mono3d_sample_results2d.pkl │ │ └── training │ │ │ ├── calib │ │ │ └── 000000.pkl │ │ │ ├── image_2 │ │ │ ├── 000000.png │ │ │ └── 000007.png │ │ │ ├── velodyne │ │ │ └── 000000.bin │ │ │ └── velodyne_reduced │ │ │ └── 000000.bin │ ├── lyft │ │ ├── lidar │ │ │ ├── host-a017_lidar1_1236118886501000046.bin │ │ │ ├── host-a017_lidar1_1236118886701083686.bin │ │ │ └── host-a017_lidar1_1236118886901125926.bin │ │ ├── lyft_infos.pkl │ │ ├── lyft_infos_val.pkl │ │ ├── sample_results.pkl │ │ ├── v1.01-train │ │ │ ├── maps │ │ │ │ └── map_raster_palo_alto.png │ │ │ └── v1.01-train │ │ │ │ ├── attribute.json │ │ │ │ ├── calibrated_sensor.json │ │ │ │ ├── category.json │ │ │ │ ├── ego_pose.json │ │ │ │ ├── instance.json │ │ │ │ ├── log.json │ │ │ │ ├── map.json │ │ │ │ ├── sample.json │ │ │ │ ├── sample_annotation.json │ │ │ │ ├── sample_data.json │ │ │ │ ├── scene.json │ │ │ │ ├── sensor.json │ │ │ │ └── visibility.json │ │ └── val.txt │ ├── nuscenes │ │ ├── mono3d_sample_results.pkl │ │ ├── nus_info.pkl │ │ ├── nus_infos_mono3d.coco.json │ │ ├── samples │ │ │ ├── CAM_BACK_LEFT │ │ │ │ └── n015-2018-07-18-11-07-57+0800__CAM_BACK_LEFT__1531883530447423.jpg │ │ │ └── LIDAR_TOP │ │ │ │ └── n015-2018-08-02-17-16-37+0800__LIDAR_TOP__1533201470948018.pcd.bin │ │ └── sweeps │ │ │ └── LIDAR_TOP │ │ │ ├── n008-2018-09-18-12-07-26-0400__LIDAR_TOP__1537287083900561.pcd.bin │ │ │ └── n015-2018-08-02-17-16-37+0800__LIDAR_TOP__1533201470898274.pcd.bin │ ├── ops │ │ ├── features_for_fps_distance.npy │ │ └── fps_idx.npy │ ├── s3dis │ │ ├── instance_mask │ │ │ └── Area_1_office_2.bin │ │ ├── points │ │ │ └── Area_1_office_2.bin │ │ ├── s3dis_infos.pkl │ │ └── semantic_mask │ │ │ └── Area_1_office_2.bin │ ├── scannet │ │ ├── instance_mask │ │ │ └── scene0000_00.bin │ │ ├── points │ │ │ └── scene0000_00.bin │ │ ├── scannet_infos.pkl │ │ └── semantic_mask │ │ │ └── scene0000_00.bin │ ├── semantickitti │ │ ├── semantickitti_infos.pkl │ │ └── sequences │ │ │ └── 00 │ │ │ ├── labels │ │ │ └── 000000.label │ │ │ └── velodyne │ │ │ └── 000000.bin │ ├── sunrgbd │ │ ├── points │ │ │ └── 000001.bin │ │ ├── sunrgbd_infos.pkl │ │ └── sunrgbd_trainval │ │ │ └── image │ │ │ └── 000001.jpg │ └── waymo │ │ ├── kitti_format │ │ ├── training │ │ │ ├── image_0 │ │ │ │ ├── 0000000.png │ │ │ │ └── 1000000.png │ │ │ └── velodyne │ │ │ │ ├── 0000000.bin │ │ │ │ └── 1000000.bin │ │ ├── waymo_dbinfos_train.pkl │ │ ├── waymo_gt_database │ │ │ └── 0_Car_0.bin │ │ ├── waymo_infos_train.pkl │ │ └── waymo_infos_val.pkl │ │ └── waymo_format │ │ ├── gt.bin │ │ └── validation │ │ └── val.tfrecord ├── test_apis │ └── test_inferencers │ │ ├── test_lidar_det3d_inferencer.py │ │ ├── test_lidar_seg3d_inferencer.py │ │ ├── test_mono_det3d_inferencer.py │ │ └── test_multi_modality_det3d_inferencer.py ├── test_datasets │ ├── test_dataset_wrappers.py │ ├── test_kitti_dataset.py │ ├── test_lyft_dataset.py │ ├── test_nuscenes_dataset.py │ ├── test_s3dis_dataset.py │ ├── test_scannet_dataset.py │ ├── test_semantickitti_dataset.py │ ├── test_sunrgbd_dataset.py │ ├── test_transforms │ │ ├── test_formating.py │ │ ├── test_loading.py │ │ ├── test_transforms_3d.py │ │ └── utils.py │ ├── test_tta.py │ └── test_waymo_dataset.py ├── test_engine │ └── test_hooks │ │ ├── test_disable_object_sample_hook.py │ │ └── test_visualization_hook.py ├── test_evaluation │ ├── test_functional │ │ ├── test_instance_seg_eval.py │ │ ├── test_kitti_eval.py │ │ ├── test_panoptic_seg_eval.py │ │ └── test_seg_eval.py │ └── test_metrics │ │ ├── test_indoor_metric.py │ │ ├── test_instance_seg_metric.py │ │ ├── test_kitti_metric.py │ │ ├── test_panoptic_seg_metric.py │ │ └── test_seg_metric.py ├── test_models │ ├── test_backbones │ │ ├── test_cylinder3d_backbone.py │ │ ├── test_dgcnn.py │ │ ├── test_dla.py │ │ ├── test_mink_resnet.py │ │ ├── test_minkunet_backbone.py │ │ ├── test_multi_backbone.py │ │ ├── test_pointnet2_sa_msg.py │ │ ├── test_pointnet2_sa_ssg.py │ │ └── test_spvcnn_backbone.py │ ├── test_data_preprocessors │ │ └── test_data_preprocessor.py │ ├── test_decode_heads │ │ ├── test_cylinder3d_head.py │ │ ├── test_dgcnn_head.py │ │ ├── test_minkunet_head.py │ │ ├── test_paconv_head.py │ │ └── test_pointnet2_head.py │ ├── test_dense_heads │ │ ├── test_anchor3d_head.py │ │ ├── test_fcaf3d_head.py │ │ ├── test_fcos_mono3d_head.py │ │ ├── test_freeanchors.py │ │ ├── test_imvoxel_head.py │ │ ├── test_monoflex_head.py │ │ ├── test_pgd_head.py │ │ ├── test_smoke_mono3d_head.py │ │ └── test_ssn.py │ ├── test_detectors │ │ ├── test_3dssd.py │ │ ├── test_center_point.py │ │ ├── test_fcaf3d.py │ │ ├── test_groupfree3d.py │ │ ├── test_h3dnet.py │ │ ├── test_imvotenet.py │ │ ├── test_imvoxelnet.py │ │ ├── test_mvxnet.py │ │ ├── test_parta2.py │ │ ├── test_pointrcnn.py │ │ ├── test_pvrcnn.py │ │ ├── test_sassd.py │ │ ├── test_votenet.py │ │ └── test_voxelnet.py │ ├── test_layers │ │ ├── test_box3d_nms.py │ │ ├── test_dgcnn_modules │ │ │ ├── test_dgcnn_fa_module.py │ │ │ ├── test_dgcnn_fp_module.py │ │ │ └── test_dgcnn_gf_module.py │ │ ├── test_fusion_layers │ │ │ ├── test_fusion_coord_trans.py │ │ │ ├── test_point_fusion.py │ │ │ └── test_vote_fusion.py │ │ ├── test_minkowski_engine │ │ │ └── test_minkowski_engine_module.py │ │ ├── test_paconv │ │ │ ├── test_paconv_modules.py │ │ │ └── test_paconv_ops.py │ │ ├── test_pointnet_modules │ │ │ ├── test_point_fp_module.py │ │ │ └── test_point_sa_module.py │ │ ├── test_spconv │ │ │ └── test_spconv_module.py │ │ ├── test_torchsparse │ │ │ └── test_torchsparse_module.py │ │ └── test_vote_module.py │ ├── test_losses │ │ ├── test_chamfer_disrance.py │ │ ├── test_multibin_loss.py │ │ ├── test_paconv_regularization_loss.py │ │ ├── test_rotated_iou_loss.py │ │ └── test_uncertain_smooth_l1_loss.py │ ├── test_middle_encoders │ │ ├── test_sparse_encoders.py │ │ └── test_sparse_unet.py │ ├── test_necks │ │ ├── test_dla_neck.py │ │ ├── test_imvoxel_neck.py │ │ ├── test_pointnet2_fp_neck.py │ │ └── test_second_fpn.py │ ├── test_segmentors │ │ ├── test_cylinder3d.py │ │ ├── test_minkunet.py │ │ └── test_seg3d_tta_model.py │ ├── test_task_modules │ │ ├── test_anchor │ │ │ └── test_anchor_3d_generator.py │ │ ├── test_coders │ │ │ ├── test_anchor_free_box_coder.py │ │ │ ├── test_centerpoint_bbox_coder.py │ │ │ ├── test_fcos3d_bbox_coder.py │ │ │ ├── test_monoflex_bbox_coder.py │ │ │ ├── test_partial_bin_based_box_coder.py │ │ │ ├── test_pgd_bbox_coder.py │ │ │ ├── test_point_xyzwhlr_bbox_coder.py │ │ │ └── test_smoke_bbox_coder.py │ │ ├── test_samplers │ │ │ └── test_iou_piecewise_sampler.py │ │ └── test_voxel │ │ │ └── test_voxel_generator.py │ ├── test_utils │ │ └── test_utils.py │ └── test_voxel_encoders │ │ ├── test_pillar_encoder.py │ │ └── test_voxel_encoders.py ├── test_samples │ └── parta2_roihead_inputs.npz ├── test_structures │ ├── test_bbox │ │ ├── test_box3d.py │ │ └── test_coord_3d_mode.py │ ├── test_det3d_data_sample.py │ ├── test_ops │ │ └── test_box_np_ops.py │ ├── test_point_data.py │ └── test_points │ │ ├── test_base_points.py │ │ ├── test_cam_points.py │ │ └── test_depth_points.py └── test_utils │ ├── test_compat_cfg.py │ └── test_setup_env.py └── tools ├── analysis_tools ├── analyze_logs.py ├── benchmark.py └── get_flops.py ├── create_data.py ├── create_data.sh ├── dataset_converters ├── create_gt_database.py ├── indoor_converter.py ├── kitti_converter.py ├── kitti_data_utils.py ├── kitti_unzip.sh ├── lyft_converter.py ├── lyft_data_fixer.py ├── nuimage_converter.py ├── nuscenes_converter.py ├── nuscenes_unzip.sh ├── s3dis_data_utils.py ├── scannet_data_utils.py ├── semantickitti_converter.py ├── semantickitti_unzip.sh ├── sunrgbd_data_utils.py ├── update_infos_to_v2.py └── waymo_converter.py ├── deployment ├── mmdet3d2torchserve.py ├── mmdet3d_handler.py └── test_torchserver.py ├── dist_test.sh ├── dist_train.sh ├── misc ├── browse_dataset.py ├── fuse_conv_bn.py ├── print_config.py └── visualize_results.py ├── model_converters ├── convert_h3dnet_checkpoints.py ├── convert_votenet_checkpoints.py ├── publish_model.py └── regnet2mmdet.py ├── slurm_test.sh ├── slurm_train.sh ├── test.py ├── train.py ├── update_data_coords.py └── update_data_coords.sh /.circleci/docker/Dockerfile: -------------------------------------------------------------------------------- 1 | ARG PYTORCH="1.8.1" 2 | ARG CUDA="10.2" 3 | ARG CUDNN="7" 4 | 5 | ARG DEBIAN_FRONTEND=noninteractive 6 | 7 | FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel 8 | 9 | # To fix GPG key error when running apt-get update 10 | RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/3bf863cc.pub 11 | RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64/7fa2af80.pub 12 | 13 | RUN apt-get update && apt-get install -y ninja-build libglib2.0-0 libsm6 libxrender-dev libxext6 libgl1-mesa-glx 14 | -------------------------------------------------------------------------------- /.dev_scripts/benchmark_options.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | 3 | third_part_libs = [ 4 | 'conda install openblas-devel -c anaconda', 5 | "pip install -U git+https://github.com/NVIDIA/MinkowskiEngine -v --no-deps --install-option='--blas_include_dirs=/opt/conda/include' --install-option='--blas=openblas'" # noqa 6 | ] 7 | default_floating_range = 0.5 8 | model_floating_ranges = { 9 | 'configs/pointpillars/pointpillars_hv_secfpn_sbn-all_16xb2-2x_waymoD5-3d-3class.py': # noqa 10 | 0.7 11 | } 12 | -------------------------------------------------------------------------------- /.dev_scripts/benchmark_train_models.txt: -------------------------------------------------------------------------------- 1 | configs/3dssd/3dssd_4xb4_kitti-3d-car.py 2 | configs/centerpoint/centerpoint_pillar02_second_secfpn_head-dcn_8xb4-cyclic-20e_nus-3d.py 3 | configs/dynamic_voxelization/second_dv_secfpn_8xb2-cosine-80e_kitti-3d-3class.py 4 | configs/fcos3d/fcos3d_r101-caffe-dcn_fpn_head-gn_8xb2-1x_nus-mono3d.py 5 | configs/mvxnet/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class.py 6 | configs/pointnet2/pointnet2_msg_2xb16-cosine-80e_s3dis-seg.py 7 | configs/pointnet2/pointnet2_msg_2xb16-cosine-250e_scannet-seg.py 8 | configs/pointpillars/pointpillars_hv_secfpn_8xb6-160e_kitti-3d-3class.py 9 | configs/pv_rcnn/pv_rcnn_8xb2-80e_kitti-3d-3class.py 10 | configs/second/second_hv_secfpn_8xb6-80e_kitti-3d-3class.py 11 | configs/second/second_hv_secfpn_8xb6-amp-80e_kitti-3d-3class.py 12 | configs/smoke/smoke_dla34_dlaneck_gn-all_4xb8-6x_kitti-mono3d.py 13 | configs/votenet/votenet_8xb8_scannet-3d.py 14 | -------------------------------------------------------------------------------- /.dev_scripts/covignore.cfg: -------------------------------------------------------------------------------- 1 | # Each line should be the relative path to the root directory 2 | # of this repo. Support regular expression as well. 3 | # For example: 4 | # .*/utils.py 5 | 6 | .*/__init__.py 7 | -------------------------------------------------------------------------------- /.dev_scripts/linter.sh: -------------------------------------------------------------------------------- 1 | yapf -r -i mmdet3d/ configs/ tests/ tools/ 2 | isort mmdet3d/ configs/ tests/ tools/ 3 | flake8 . 4 | -------------------------------------------------------------------------------- /.github/CONTRIBUTING.md: -------------------------------------------------------------------------------- 1 | We appreciate all contributions to improve MMDetection3D. 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://mmdetection3d.readthedocs.io/en/latest/notes/faq.html 6 | about: Check if your issue already has solutions 7 | - name: MMDet3D Documentation 8 | url: https://mmdetection3d.readthedocs.io/en/latest/ 9 | about: Check if your question is answered in docs 10 | -------------------------------------------------------------------------------- /.github/workflows/deploy.yml: -------------------------------------------------------------------------------- 1 | name: deploy 2 | 3 | on: push 4 | 5 | concurrency: 6 | group: ${{ github.workflow }}-${{ github.ref }} 7 | cancel-in-progress: true 8 | 9 | jobs: 10 | build-n-publish: 11 | runs-on: ubuntu-latest 12 | if: startsWith(github.event.ref, 'refs/tags') 13 | steps: 14 | - uses: actions/checkout@v2 15 | - name: Set up Python 3.7 16 | uses: actions/setup-python@v2 17 | with: 18 | python-version: 3.7 19 | - name: Install torch 20 | run: pip install torch 21 | - name: Install wheel 22 | run: pip install wheel 23 | - name: Build MMDet3D 24 | run: python setup.py sdist bdist_wheel 25 | - name: Publish distribution to PyPI 26 | run: | 27 | pip install twine 28 | twine upload dist/* -u __token__ -p ${{ secrets.pypi_password }} 29 | -------------------------------------------------------------------------------- /.github/workflows/lint.yml: -------------------------------------------------------------------------------- 1 | name: lint 2 | 3 | on: [push, pull_request] 4 | 5 | concurrency: 6 | group: ${{ github.workflow }}-${{ github.ref }} 7 | cancel-in-progress: true 8 | 9 | jobs: 10 | lint: 11 | runs-on: ubuntu-latest 12 | steps: 13 | - uses: actions/checkout@v2 14 | - name: Set up Python 3.7 15 | uses: actions/setup-python@v2 16 | with: 17 | python-version: 3.7 18 | - name: Install pre-commit hook 19 | run: | 20 | pip install pre-commit 21 | pre-commit install 22 | - name: Linting 23 | run: pre-commit run --all-files 24 | - name: Check docstring coverage 25 | run: | 26 | pip install interrogate 27 | interrogate -v --ignore-init-method --ignore-magic --ignore-module --ignore-nested-functions --ignore-regex "__repr__" --fail-under 90 mmdet3d 28 | -------------------------------------------------------------------------------- /.readthedocs.yml: -------------------------------------------------------------------------------- 1 | version: 2 2 | 3 | build: 4 | os: ubuntu-22.04 5 | tools: 6 | python: "3.8" 7 | 8 | formats: 9 | - epub 10 | 11 | python: 12 | install: 13 | - requirements: requirements/docs.txt 14 | - requirements: requirements/readthedocs.txt 15 | -------------------------------------------------------------------------------- /CITATION.cff: -------------------------------------------------------------------------------- 1 | cff-version: 1.2.0 2 | message: "If you use this software, please cite it as below." 3 | authors: 4 | - name: "MMDetection3D Contributors" 5 | title: "OpenMMLab's Next-generation Platform for General 3D Object Detection" 6 | date-released: 2020-07-23 7 | url: "https://github.com/open-mmlab/mmdetection3d" 8 | license: Apache-2.0 9 | -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- 1 | include mmdet3d/.mim/model-index.yml 2 | include mmdet3d/.mim/dataset-index.yml 3 | include requirements/*.txt 4 | recursive-include mmdet3d/.mim/ops *.cpp *.cu *.h *.cc 5 | recursive-include mmdet3d/.mim/configs *.py *.yml 6 | recursive-include mmdet3d/.mim/tools *.sh *.py 7 | -------------------------------------------------------------------------------- /configs/3dssd/metafile.yml: -------------------------------------------------------------------------------- 1 | Collections: 2 | - Name: 3DSSD 3 | Metadata: 4 | Training Data: KITTI 5 | Training Techniques: 6 | - AdamW 7 | Training Resources: 4x TITAN X 8 | Architecture: 9 | - PointNet++ 10 | Paper: 11 | URL: https://arxiv.org/abs/2002.10187 12 | Title: '3DSSD: Point-based 3D Single Stage Object Detector' 13 | README: configs/3dssd/README.md 14 | Code: 15 | URL: https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/models/detectors/ssd3dnet.py#L7 16 | Version: v0.6.0 17 | 18 | Models: 19 | - Name: 3dssd_4x4_kitti-3d-car 20 | In Collection: 3DSSD 21 | Config: configs/3dssd/3dssd_4xb4_kitti-3d-car.py 22 | Metadata: 23 | Training Memory (GB): 4.7 24 | Results: 25 | - Task: 3D Object Detection 26 | Dataset: KITTI 27 | Metrics: 28 | mAP: 78.58 29 | Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/3dssd/3dssd_4x4_kitti-3d-car/3dssd_4x4_kitti-3d-car_20210818_203828-b89c8fc4.pth 30 | -------------------------------------------------------------------------------- /configs/_base_/default_runtime.py: -------------------------------------------------------------------------------- 1 | default_scope = 'mmdet3d' 2 | 3 | default_hooks = dict( 4 | timer=dict(type='IterTimerHook'), 5 | logger=dict(type='LoggerHook', interval=50), 6 | param_scheduler=dict(type='ParamSchedulerHook'), 7 | checkpoint=dict(type='CheckpointHook', interval=-1), 8 | sampler_seed=dict(type='DistSamplerSeedHook'), 9 | visualization=dict(type='Det3DVisualizationHook')) 10 | 11 | env_cfg = dict( 12 | cudnn_benchmark=False, 13 | mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), 14 | dist_cfg=dict(backend='nccl'), 15 | ) 16 | 17 | log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True) 18 | 19 | log_level = 'INFO' 20 | load_from = None 21 | resume = False 22 | 23 | # TODO: support auto scaling lr 24 | -------------------------------------------------------------------------------- /configs/_base_/models/dgcnn.py: -------------------------------------------------------------------------------- 1 | # model settings 2 | model = dict( 3 | type='EncoderDecoder3D', 4 | data_preprocessor=dict(type='Det3DDataPreprocessor'), 5 | backbone=dict( 6 | type='DGCNNBackbone', 7 | in_channels=9, # [xyz, rgb, normal_xyz], modified with dataset 8 | num_samples=(20, 20, 20), 9 | knn_modes=('D-KNN', 'F-KNN', 'F-KNN'), 10 | radius=(None, None, None), 11 | gf_channels=((64, 64), (64, 64), (64, )), 12 | fa_channels=(1024, ), 13 | act_cfg=dict(type='LeakyReLU', negative_slope=0.2)), 14 | decode_head=dict( 15 | type='DGCNNHead', 16 | fp_channels=(1216, 512), 17 | channels=256, 18 | dropout_ratio=0.5, 19 | conv_cfg=dict(type='Conv1d'), 20 | norm_cfg=dict(type='BN1d'), 21 | act_cfg=dict(type='LeakyReLU', negative_slope=0.2), 22 | loss_decode=dict( 23 | type='mmdet.CrossEntropyLoss', 24 | use_sigmoid=False, 25 | class_weight=None, # modified with dataset 26 | loss_weight=1.0)), 27 | # model training and testing settings 28 | train_cfg=dict(), 29 | test_cfg=dict(mode='slide')) 30 | -------------------------------------------------------------------------------- /configs/_base_/models/fcaf3d.py: -------------------------------------------------------------------------------- 1 | model = dict( 2 | type='MinkSingleStage3DDetector', 3 | data_preprocessor=dict(type='Det3DDataPreprocessor'), 4 | backbone=dict(type='MinkResNet', in_channels=3, depth=34), 5 | bbox_head=dict( 6 | type='FCAF3DHead', 7 | in_channels=(64, 128, 256, 512), 8 | out_channels=128, 9 | voxel_size=.01, 10 | pts_prune_threshold=100000, 11 | pts_assign_threshold=27, 12 | pts_center_threshold=18, 13 | num_classes=18, 14 | num_reg_outs=6, 15 | center_loss=dict(type='mmdet.CrossEntropyLoss', use_sigmoid=True), 16 | bbox_loss=dict(type='AxisAlignedIoULoss'), 17 | cls_loss=dict(type='mmdet.FocalLoss'), 18 | ), 19 | train_cfg=dict(), 20 | test_cfg=dict(nms_pre=1000, iou_thr=.5, score_thr=.01)) 21 | -------------------------------------------------------------------------------- /configs/_base_/models/minkunet.py: -------------------------------------------------------------------------------- 1 | model = dict( 2 | type='MinkUNet', 3 | data_preprocessor=dict( 4 | type='Det3DDataPreprocessor', 5 | voxel=True, 6 | voxel_type='minkunet', 7 | batch_first=False, 8 | max_voxels=80000, 9 | voxel_layer=dict( 10 | max_num_points=-1, 11 | point_cloud_range=[-100, -100, -20, 100, 100, 20], 12 | voxel_size=[0.05, 0.05, 0.05], 13 | max_voxels=(-1, -1))), 14 | backbone=dict( 15 | type='MinkUNetBackbone', 16 | in_channels=4, 17 | num_stages=4, 18 | base_channels=32, 19 | encoder_channels=[32, 64, 128, 256], 20 | encoder_blocks=[2, 2, 2, 2], 21 | decoder_channels=[256, 128, 96, 96], 22 | decoder_blocks=[2, 2, 2, 2], 23 | block_type='basic', 24 | sparseconv_backend='torchsparse'), 25 | decode_head=dict( 26 | type='MinkUNetHead', 27 | channels=96, 28 | num_classes=19, 29 | dropout_ratio=0, 30 | loss_decode=dict(type='mmdet.CrossEntropyLoss', avg_non_ignore=True), 31 | ignore_index=19), 32 | train_cfg=dict(), 33 | test_cfg=dict()) 34 | -------------------------------------------------------------------------------- /configs/_base_/models/paconv_ssg-cuda.py: -------------------------------------------------------------------------------- 1 | _base_ = './paconv_ssg.py' 2 | 3 | model = dict( 4 | backbone=dict( 5 | sa_cfg=dict( 6 | type='PAConvCUDASAModule', 7 | scorenet_cfg=dict(mlp_channels=[8, 16, 16])))) 8 | -------------------------------------------------------------------------------- /configs/_base_/models/pointpillars_hv_fpn_lyft.py: -------------------------------------------------------------------------------- 1 | _base_ = './pointpillars_hv_fpn_nus.py' 2 | 3 | # model settings (based on nuScenes model settings) 4 | # Voxel size for voxel encoder 5 | # Usually voxel size is changed consistently with the point cloud range 6 | # If point cloud range is modified, do remember to change all related 7 | # keys in the config. 8 | model = dict( 9 | data_preprocessor=dict( 10 | voxel_layer=dict( 11 | max_num_points=20, 12 | point_cloud_range=[-80, -80, -5, 80, 80, 3], 13 | max_voxels=(60000, 60000))), 14 | pts_voxel_encoder=dict( 15 | feat_channels=[64], point_cloud_range=[-80, -80, -5, 80, 80, 3]), 16 | pts_middle_encoder=dict(output_shape=[640, 640]), 17 | pts_bbox_head=dict( 18 | num_classes=9, 19 | anchor_generator=dict( 20 | ranges=[[-80, -80, -1.8, 80, 80, -1.8]], custom_values=[]), 21 | bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder', code_size=7)), 22 | # model training settings (based on nuScenes model settings) 23 | train_cfg=dict(pts=dict(code_weight=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]))) 24 | -------------------------------------------------------------------------------- /configs/_base_/models/pointpillars_hv_fpn_range100_lyft.py: -------------------------------------------------------------------------------- 1 | _base_ = './pointpillars_hv_fpn_nus.py' 2 | 3 | # model settings (based on nuScenes model settings) 4 | # Voxel size for voxel encoder 5 | # Usually voxel size is changed consistently with the point cloud range 6 | # If point cloud range is modified, do remember to change all related 7 | # keys in the config. 8 | model = dict( 9 | data_preprocessor=dict( 10 | voxel_layer=dict( 11 | max_num_points=20, 12 | point_cloud_range=[-100, -100, -5, 100, 100, 3], 13 | max_voxels=(60000, 60000))), 14 | pts_voxel_encoder=dict( 15 | feat_channels=[64], point_cloud_range=[-100, -100, -5, 100, 100, 3]), 16 | pts_middle_encoder=dict(output_shape=[800, 800]), 17 | pts_bbox_head=dict( 18 | num_classes=9, 19 | anchor_generator=dict( 20 | ranges=[[-100, -100, -1.8, 100, 100, -1.8]], custom_values=[]), 21 | bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder', code_size=7)), 22 | # model training settings (based on nuScenes model settings) 23 | train_cfg=dict(pts=dict(code_weight=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]))) 24 | -------------------------------------------------------------------------------- /configs/_base_/models/spvcnn.py: -------------------------------------------------------------------------------- 1 | model = dict( 2 | type='MinkUNet', 3 | data_preprocessor=dict( 4 | type='Det3DDataPreprocessor', 5 | voxel=True, 6 | voxel_type='minkunet', 7 | batch_first=False, 8 | max_voxels=80000, 9 | voxel_layer=dict( 10 | max_num_points=-1, 11 | point_cloud_range=[-100, -100, -20, 100, 100, 20], 12 | voxel_size=[0.05, 0.05, 0.05], 13 | max_voxels=(-1, -1))), 14 | backbone=dict( 15 | type='SPVCNNBackbone', 16 | in_channels=4, 17 | num_stages=4, 18 | base_channels=32, 19 | encoder_channels=[32, 64, 128, 256], 20 | encoder_blocks=[2, 2, 2, 2], 21 | decoder_channels=[256, 128, 96, 96], 22 | decoder_blocks=[2, 2, 2, 2], 23 | block_type='basic', 24 | sparseconv_backend='torchsparse', 25 | drop_ratio=0.3), 26 | decode_head=dict( 27 | type='MinkUNetHead', 28 | channels=96, 29 | num_classes=19, 30 | dropout_ratio=0, 31 | loss_decode=dict(type='mmdet.CrossEntropyLoss', avg_non_ignore=True), 32 | ignore_index=19), 33 | train_cfg=dict(), 34 | test_cfg=dict()) 35 | -------------------------------------------------------------------------------- /configs/_base_/schedules/cosine.py: -------------------------------------------------------------------------------- 1 | # This schedule is mainly used by models with dynamic voxelization 2 | # optimizer 3 | lr = 0.003 # max learning rate 4 | optim_wrapper = dict( 5 | type='OptimWrapper', 6 | optimizer=dict( 7 | type='AdamW', lr=lr, weight_decay=0.001, betas=(0.95, 0.99)), 8 | clip_grad=dict(max_norm=10, norm_type=2), 9 | ) 10 | 11 | param_scheduler = [ 12 | dict(type='LinearLR', start_factor=0.1, by_epoch=False, begin=0, end=1000), 13 | dict( 14 | type='CosineAnnealingLR', 15 | begin=0, 16 | T_max=40, 17 | end=40, 18 | by_epoch=True, 19 | eta_min=1e-5) 20 | ] 21 | # training schedule for 1x 22 | train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=40, val_interval=1) 23 | val_cfg = dict(type='ValLoop') 24 | test_cfg = dict(type='TestLoop') 25 | 26 | # Default setting for scaling LR automatically 27 | # - `enable` means enable scaling LR automatically 28 | # or not by default. 29 | # - `base_batch_size` = (8 GPUs) x (2 samples per GPU). 30 | auto_scale_lr = dict(enable=False, base_batch_size=16) 31 | -------------------------------------------------------------------------------- /configs/_base_/schedules/mmdet-schedule-1x.py: -------------------------------------------------------------------------------- 1 | # training schedule for 1x 2 | train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=1) 3 | val_cfg = dict(type='ValLoop') 4 | test_cfg = dict(type='TestLoop') 5 | 6 | # learning rate 7 | param_scheduler = [ 8 | dict( 9 | type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500), 10 | dict( 11 | type='MultiStepLR', 12 | begin=0, 13 | end=12, 14 | by_epoch=True, 15 | milestones=[8, 11], 16 | gamma=0.1) 17 | ] 18 | 19 | # optimizer 20 | optim_wrapper = dict( 21 | type='OptimWrapper', 22 | optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)) 23 | 24 | # Default setting for scaling LR automatically 25 | # - `enable` means enable scaling LR automatically 26 | # or not by default. 27 | # - `base_batch_size` = (8 GPUs) x (2 samples per GPU). 28 | auto_scale_lr = dict(enable=False, base_batch_size=16) 29 | -------------------------------------------------------------------------------- /configs/_base_/schedules/schedule-2x.py: -------------------------------------------------------------------------------- 1 | # optimizer 2 | # This schedule is mainly used by models on nuScenes dataset 3 | lr = 0.001 4 | optim_wrapper = dict( 5 | type='OptimWrapper', 6 | optimizer=dict(type='AdamW', lr=lr, weight_decay=0.01), 7 | # max_norm=10 is better for SECOND 8 | clip_grad=dict(max_norm=35, norm_type=2)) 9 | 10 | # training schedule for 2x 11 | train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=24, val_interval=24) 12 | val_cfg = dict(type='ValLoop') 13 | test_cfg = dict(type='TestLoop') 14 | 15 | # learning rate 16 | param_scheduler = [ 17 | dict( 18 | type='LinearLR', 19 | start_factor=1.0 / 1000, 20 | by_epoch=False, 21 | begin=0, 22 | end=1000), 23 | dict( 24 | type='MultiStepLR', 25 | begin=0, 26 | end=24, 27 | by_epoch=True, 28 | milestones=[20, 23], 29 | gamma=0.1) 30 | ] 31 | 32 | # Default setting for scaling LR automatically 33 | # - `enable` means enable scaling LR automatically 34 | # or not by default. 35 | # - `base_batch_size` = (8 GPUs) x (4 samples per GPU). 36 | auto_scale_lr = dict(enable=False, base_batch_size=32) 37 | -------------------------------------------------------------------------------- /configs/_base_/schedules/schedule-3x.py: -------------------------------------------------------------------------------- 1 | # optimizer 2 | # This schedule is mainly used by models on indoor dataset, 3 | # e.g., VoteNet on SUNRGBD and ScanNet 4 | lr = 0.008 # max learning rate 5 | optim_wrapper = dict( 6 | type='OptimWrapper', 7 | optimizer=dict(type='AdamW', lr=lr, weight_decay=0.01), 8 | clip_grad=dict(max_norm=10, norm_type=2), 9 | ) 10 | 11 | # training schedule for 3x 12 | train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=36, val_interval=1) 13 | val_cfg = dict(type='ValLoop') 14 | test_cfg = dict(type='TestLoop') 15 | 16 | # learning rate 17 | param_scheduler = [ 18 | dict( 19 | type='MultiStepLR', 20 | begin=0, 21 | end=36, 22 | by_epoch=True, 23 | milestones=[24, 32], 24 | gamma=0.1) 25 | ] 26 | 27 | # Default setting for scaling LR automatically 28 | # - `enable` means enable scaling LR automatically 29 | # or not by default. 30 | # - `base_batch_size` = (4 GPUs) x (8 samples per GPU). 31 | auto_scale_lr = dict(enable=False, base_batch_size=32) 32 | -------------------------------------------------------------------------------- /configs/_base_/schedules/seg-cosine-100e.py: -------------------------------------------------------------------------------- 1 | # optimizer 2 | # This schedule is mainly used on S3DIS dataset in segmentation task 3 | optim_wrapper = dict( 4 | type='OptimWrapper', 5 | optimizer=dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.001), 6 | clip_grad=None) 7 | 8 | param_scheduler = [ 9 | dict( 10 | type='CosineAnnealingLR', 11 | T_max=100, 12 | eta_min=1e-5, 13 | by_epoch=True, 14 | begin=0, 15 | end=100) 16 | ] 17 | 18 | # runtime settings 19 | train_cfg = dict(by_epoch=True, max_epochs=100, val_interval=1) 20 | val_cfg = dict() 21 | test_cfg = dict() 22 | 23 | # Default setting for scaling LR automatically 24 | # - `enable` means enable scaling LR automatically 25 | # or not by default. 26 | # - `base_batch_size` = (4 GPUs) x (32 samples per GPU). 27 | auto_scale_lr = dict(enable=False, base_batch_size=128) 28 | -------------------------------------------------------------------------------- /configs/_base_/schedules/seg-cosine-150e.py: -------------------------------------------------------------------------------- 1 | # optimizer 2 | # This schedule is mainly used on S3DIS dataset in segmentation task 3 | optim_wrapper = dict( 4 | type='OptimWrapper', 5 | optimizer=dict(type='SGD', lr=0.2, momentum=0.9, weight_decay=0.0001), 6 | clip_grad=None) 7 | 8 | param_scheduler = [ 9 | dict( 10 | type='CosineAnnealingLR', 11 | T_max=150, 12 | eta_min=0.002, 13 | by_epoch=True, 14 | begin=0, 15 | end=150) 16 | ] 17 | 18 | # runtime settings 19 | train_cfg = dict(by_epoch=True, max_epochs=150, val_interval=1) 20 | val_cfg = dict() 21 | test_cfg = dict() 22 | 23 | # Default setting for scaling LR automatically 24 | # - `enable` means enable scaling LR automatically 25 | # or not by default. 26 | # - `base_batch_size` = (8 GPUs) x (8 samples per GPU). 27 | auto_scale_lr = dict(enable=False, base_batch_size=64) 28 | -------------------------------------------------------------------------------- /configs/_base_/schedules/seg-cosine-200e.py: -------------------------------------------------------------------------------- 1 | # optimizer 2 | # This schedule is mainly used on S3DIS dataset in segmentation task 3 | optim_wrapper = dict( 4 | type='OptimWrapper', 5 | optimizer=dict(type='Adam', lr=0.001, weight_decay=0.01), 6 | clip_grad=None) 7 | 8 | param_scheduler = [ 9 | dict( 10 | type='CosineAnnealingLR', 11 | T_max=200, 12 | eta_min=1e-5, 13 | by_epoch=True, 14 | begin=0, 15 | end=200) 16 | ] 17 | 18 | # runtime settings 19 | train_cfg = dict(by_epoch=True, max_epochs=200, val_interval=1) 20 | val_cfg = dict() 21 | test_cfg = dict() 22 | 23 | # Default setting for scaling LR automatically 24 | # - `enable` means enable scaling LR automatically 25 | # or not by default. 26 | # - `base_batch_size` = (2 GPUs) x (16 samples per GPU). 27 | auto_scale_lr = dict(enable=False, base_batch_size=32) 28 | -------------------------------------------------------------------------------- /configs/_base_/schedules/seg-cosine-50e.py: -------------------------------------------------------------------------------- 1 | # optimizer 2 | # This schedule is mainly used on S3DIS dataset in segmentation task 3 | optim_wrapper = dict( 4 | type='OptimWrapper', 5 | optimizer=dict(type='Adam', lr=0.001, weight_decay=0.001), 6 | clip_grad=None) 7 | 8 | param_scheduler = [ 9 | dict( 10 | type='CosineAnnealingLR', 11 | T_max=50, 12 | eta_min=1e-5, 13 | by_epoch=True, 14 | begin=0, 15 | end=50) 16 | ] 17 | 18 | # runtime settings 19 | train_cfg = dict(by_epoch=True, max_epochs=50, val_interval=1) 20 | val_cfg = dict() 21 | test_cfg = dict() 22 | 23 | # Default setting for scaling LR automatically 24 | # - `enable` means enable scaling LR automatically 25 | # or not by default. 26 | # - `base_batch_size` = (2 GPUs) x (16 samples per GPU). 27 | auto_scale_lr = dict(enable=False, base_batch_size=32) 28 | -------------------------------------------------------------------------------- /configs/centerpoint/centerpoint_pillar02_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./centerpoint_pillar02_second_secfpn_8xb4-cyclic-20e_nus-3d.py'] 2 | 3 | model = dict(test_cfg=dict(pts=dict(nms_type='circle'))) 4 | -------------------------------------------------------------------------------- /configs/centerpoint/centerpoint_pillar02_second_secfpn_head-dcn-circlenms_8xb4-cyclic-20e_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./centerpoint_pillar02_second_secfpn_8xb4-cyclic-20e_nus-3d.py'] 2 | 3 | model = dict( 4 | pts_bbox_head=dict( 5 | separate_head=dict( 6 | type='DCNSeparateHead', 7 | dcn_config=dict( 8 | type='DCN', 9 | in_channels=64, 10 | out_channels=64, 11 | kernel_size=3, 12 | padding=1, 13 | groups=4), 14 | init_bias=-2.19, 15 | final_kernel=3)), 16 | test_cfg=dict(pts=dict(nms_type='circle'))) 17 | -------------------------------------------------------------------------------- /configs/centerpoint/centerpoint_pillar02_second_secfpn_head-dcn_8xb4-cyclic-20e_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./centerpoint_pillar02_second_secfpn_8xb4-cyclic-20e_nus-3d.py'] 2 | 3 | model = dict( 4 | pts_bbox_head=dict( 5 | separate_head=dict( 6 | type='DCNSeparateHead', 7 | dcn_config=dict( 8 | type='DCN', 9 | in_channels=64, 10 | out_channels=64, 11 | kernel_size=3, 12 | padding=1, 13 | groups=4), 14 | init_bias=-2.19, 15 | final_kernel=3))) 16 | -------------------------------------------------------------------------------- /configs/centerpoint/centerpoint_voxel0075_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./centerpoint_voxel0075_second_secfpn_8xb4-cyclic-20e_nus-3d.py'] 2 | 3 | model = dict(test_cfg=dict(pts=dict(nms_type='circle'))) 4 | -------------------------------------------------------------------------------- /configs/centerpoint/centerpoint_voxel0075_second_secfpn_head-dcn-circlenms_8xb4-cyclic-20e_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./centerpoint_voxel0075_second_secfpn_8xb4-cyclic-20e_nus-3d.py'] 2 | 3 | model = dict( 4 | pts_bbox_head=dict( 5 | separate_head=dict( 6 | type='DCNSeparateHead', 7 | dcn_config=dict( 8 | type='DCN', 9 | in_channels=64, 10 | out_channels=64, 11 | kernel_size=3, 12 | padding=1, 13 | groups=4), 14 | init_bias=-2.19, 15 | final_kernel=3)), 16 | test_cfg=dict(pts=dict(nms_type='circle'))) 17 | -------------------------------------------------------------------------------- /configs/centerpoint/centerpoint_voxel0075_second_secfpn_head-dcn_8xb4-cyclic-20e_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./centerpoint_voxel0075_second_secfpn_8xb4-cyclic-20e_nus-3d.py'] 2 | 3 | model = dict( 4 | pts_bbox_head=dict( 5 | separate_head=dict( 6 | type='DCNSeparateHead', 7 | dcn_config=dict( 8 | type='DCN', 9 | in_channels=64, 10 | out_channels=64, 11 | kernel_size=3, 12 | padding=1, 13 | groups=4), 14 | init_bias=-2.19, 15 | final_kernel=3))) 16 | -------------------------------------------------------------------------------- /configs/centerpoint/centerpoint_voxel01_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./centerpoint_voxel01_second_secfpn_8xb4-cyclic-20e_nus-3d.py'] 2 | 3 | model = dict(test_cfg=dict(pts=dict(nms_type='circle'))) 4 | -------------------------------------------------------------------------------- /configs/centerpoint/centerpoint_voxel01_second_secfpn_head-dcn-circlenms_8xb4-cyclic-20e_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./centerpoint_voxel01_second_secfpn_8xb4-cyclic-20e_nus-3d.py'] 2 | 3 | model = dict( 4 | pts_bbox_head=dict( 5 | separate_head=dict( 6 | type='DCNSeparateHead', 7 | dcn_config=dict( 8 | type='DCN', 9 | in_channels=64, 10 | out_channels=64, 11 | kernel_size=3, 12 | padding=1, 13 | groups=4), 14 | init_bias=-2.19, 15 | final_kernel=3)), 16 | test_cfg=dict(pts=dict(nms_type='circle'))) 17 | -------------------------------------------------------------------------------- /configs/centerpoint/centerpoint_voxel01_second_secfpn_head-dcn_8xb4-cyclic-20e_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./centerpoint_voxel01_second_secfpn_8xb4-cyclic-20e_nus-3d.py'] 2 | 3 | model = dict( 4 | pts_bbox_head=dict( 5 | separate_head=dict( 6 | type='DCNSeparateHead', 7 | dcn_config=dict( 8 | type='DCN', 9 | in_channels=64, 10 | out_channels=64, 11 | kernel_size=3, 12 | padding=1, 13 | groups=4), 14 | init_bias=-2.19, 15 | final_kernel=3))) 16 | -------------------------------------------------------------------------------- /configs/cylinder3d/cylinder3d_4xb4-3x_semantickitti.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/datasets/semantickitti.py', '../_base_/models/cylinder3d.py', 3 | '../_base_/default_runtime.py' 4 | ] 5 | 6 | # optimizer 7 | lr = 0.001 8 | optim_wrapper = dict( 9 | type='OptimWrapper', 10 | optimizer=dict(type='AdamW', lr=lr, weight_decay=0.01)) 11 | 12 | train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=36, val_interval=1) 13 | val_cfg = dict(type='ValLoop') 14 | test_cfg = dict(type='TestLoop') 15 | 16 | # learning rate 17 | param_scheduler = [ 18 | dict( 19 | type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, 20 | end=1000), 21 | dict( 22 | type='MultiStepLR', 23 | begin=0, 24 | end=36, 25 | by_epoch=True, 26 | milestones=[30], 27 | gamma=0.1) 28 | ] 29 | 30 | train_dataloader = dict(batch_size=4, ) 31 | 32 | # Default setting for scaling LR automatically 33 | # - `enable` means enable scaling LR automatically 34 | # or not by default. 35 | # - `base_batch_size` = (8 GPUs) x (4 samples per GPU). 36 | # auto_scale_lr = dict(enable=False, base_batch_size=32) 37 | 38 | default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=5)) 39 | -------------------------------------------------------------------------------- /configs/dgcnn/dgcnn_4xb32-cosine-100e_s3dis-seg_test-area1.py: -------------------------------------------------------------------------------- 1 | _base_ = './dgcnn_4xb32-cosine-100e_s3dis-seg_test-area5.py' 2 | 3 | # data settings 4 | train_area = [2, 3, 4, 5, 6] 5 | test_area = 1 6 | train_dataloader = dict( 7 | batch_size=32, 8 | dataset=dict( 9 | ann_files=[f's3dis_infos_Area_{i}.pkl' for i in train_area], 10 | scene_idxs=[ 11 | f'seg_info/Area_{i}_resampled_scene_idxs.npy' for i in train_area 12 | ])) 13 | test_dataloader = dict( 14 | dataset=dict( 15 | ann_files=f's3dis_infos_Area_{test_area}.pkl', 16 | scene_idxs=f'seg_info/Area_{test_area}_resampled_scene_idxs.npy')) 17 | val_dataloader = test_dataloader 18 | -------------------------------------------------------------------------------- /configs/dgcnn/dgcnn_4xb32-cosine-100e_s3dis-seg_test-area2.py: -------------------------------------------------------------------------------- 1 | _base_ = './dgcnn_4xb32-cosine-100e_s3dis-seg_test-area5.py' 2 | 3 | # data settings 4 | train_area = [1, 3, 4, 5, 6] 5 | test_area = 2 6 | train_dataloader = dict( 7 | batch_size=32, 8 | dataset=dict( 9 | ann_files=[f's3dis_infos_Area_{i}.pkl' for i in train_area], 10 | scene_idxs=[ 11 | f'seg_info/Area_{i}_resampled_scene_idxs.npy' for i in train_area 12 | ])) 13 | test_dataloader = dict( 14 | dataset=dict( 15 | ann_files=f's3dis_infos_Area_{test_area}.pkl', 16 | scene_idxs=f'seg_info/Area_{test_area}_resampled_scene_idxs.npy')) 17 | val_dataloader = test_dataloader 18 | -------------------------------------------------------------------------------- /configs/dgcnn/dgcnn_4xb32-cosine-100e_s3dis-seg_test-area3.py: -------------------------------------------------------------------------------- 1 | _base_ = './dgcnn_4xb32-cosine-100e_s3dis-seg_test-area5.py' 2 | 3 | # data settings 4 | train_area = [1, 2, 4, 5, 6] 5 | test_area = 3 6 | train_dataloader = dict( 7 | batch_size=32, 8 | dataset=dict( 9 | ann_files=[f's3dis_infos_Area_{i}.pkl' for i in train_area], 10 | scene_idxs=[ 11 | f'seg_info/Area_{i}_resampled_scene_idxs.npy' for i in train_area 12 | ])) 13 | test_dataloader = dict( 14 | dataset=dict( 15 | ann_files=f's3dis_infos_Area_{test_area}.pkl', 16 | scene_idxs=f'seg_info/Area_{test_area}_resampled_scene_idxs.npy')) 17 | val_dataloader = test_dataloader 18 | -------------------------------------------------------------------------------- /configs/dgcnn/dgcnn_4xb32-cosine-100e_s3dis-seg_test-area4.py: -------------------------------------------------------------------------------- 1 | _base_ = './dgcnn_4xb32-cosine-100e_s3dis-seg_test-area5.py' 2 | 3 | # data settings 4 | train_area = [1, 2, 3, 5, 6] 5 | test_area = 4 6 | train_dataloader = dict( 7 | batch_size=32, 8 | dataset=dict( 9 | ann_files=[f's3dis_infos_Area_{i}.pkl' for i in train_area], 10 | scene_idxs=[ 11 | f'seg_info/Area_{i}_resampled_scene_idxs.npy' for i in train_area 12 | ])) 13 | test_dataloader = dict( 14 | dataset=dict( 15 | ann_files=f's3dis_infos_Area_{test_area}.pkl', 16 | scene_idxs=f'seg_info/Area_{test_area}_resampled_scene_idxs.npy')) 17 | val_dataloader = test_dataloader 18 | -------------------------------------------------------------------------------- /configs/dgcnn/dgcnn_4xb32-cosine-100e_s3dis-seg_test-area5.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/datasets/s3dis-seg.py', '../_base_/models/dgcnn.py', 3 | '../_base_/schedules/seg-cosine-100e.py', '../_base_/default_runtime.py' 4 | ] 5 | 6 | # model settings 7 | model = dict( 8 | backbone=dict(in_channels=9), # [xyz, rgb, normalized_xyz] 9 | decode_head=dict( 10 | num_classes=13, ignore_index=13, 11 | loss_decode=dict(class_weight=None)), # S3DIS doesn't use class_weight 12 | test_cfg=dict( 13 | num_points=4096, 14 | block_size=1.0, 15 | sample_rate=0.5, 16 | use_normalized_coord=True, 17 | batch_size=24)) 18 | 19 | default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=2)) 20 | train_dataloader = dict(batch_size=32) 21 | train_cfg = dict(val_interval=2) 22 | -------------------------------------------------------------------------------- /configs/dgcnn/dgcnn_4xb32-cosine-100e_s3dis-seg_test-area6.py: -------------------------------------------------------------------------------- 1 | _base_ = './dgcnn_4xb32-cosine-100e_s3dis-seg_test-area5.py' 2 | 3 | # data settings 4 | train_area = [1, 2, 3, 4, 5] 5 | test_area = 6 6 | train_dataloader = dict( 7 | batch_size=32, 8 | dataset=dict( 9 | ann_files=[f's3dis_infos_Area_{i}.pkl' for i in train_area], 10 | scene_idxs=[ 11 | f'seg_info/Area_{i}_resampled_scene_idxs.npy' for i in train_area 12 | ])) 13 | test_dataloader = dict( 14 | dataset=dict( 15 | ann_files=f's3dis_infos_Area_{test_area}.pkl', 16 | scene_idxs=f'seg_info/Area_{test_area}_resampled_scene_idxs.npy')) 17 | val_dataloader = test_dataloader 18 | -------------------------------------------------------------------------------- /configs/dynamic_voxelization/pointpillars_dv_secfpn_8xb6-160e_kitti-3d-car.py: -------------------------------------------------------------------------------- 1 | _base_ = '../pointpillars/pointpillars_hv_secfpn_8xb6-160e_kitti-3d-car.py' 2 | 3 | voxel_size = [0.16, 0.16, 4] 4 | point_cloud_range = [0, -39.68, -3, 69.12, 39.68, 1] 5 | 6 | model = dict( 7 | type='DynamicVoxelNet', 8 | data_preprocessor=dict( 9 | voxel_type='dynamic', 10 | voxel_layer=dict( 11 | max_num_points=-1, 12 | point_cloud_range=point_cloud_range, 13 | voxel_size=voxel_size, 14 | max_voxels=(-1, -1))), 15 | voxel_encoder=dict( 16 | type='DynamicPillarFeatureNet', 17 | in_channels=4, 18 | feat_channels=[64], 19 | with_distance=False, 20 | voxel_size=voxel_size, 21 | point_cloud_range=point_cloud_range)) 22 | -------------------------------------------------------------------------------- /configs/dynamic_voxelization/second_dv_secfpn_8xb2-cosine-80e_kitti-3d-3class.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/second_hv_secfpn_kitti.py', 3 | '../_base_/datasets/kitti-3d-3class.py', '../_base_/schedules/cosine.py', 4 | '../_base_/default_runtime.py' 5 | ] 6 | 7 | point_cloud_range = [0, -40, -3, 70.4, 40, 1] 8 | voxel_size = [0.05, 0.05, 0.1] 9 | 10 | model = dict( 11 | type='DynamicVoxelNet', 12 | data_preprocessor=dict( 13 | voxel_type='dynamic', 14 | voxel_layer=dict( 15 | _delete_=True, 16 | max_num_points=-1, 17 | point_cloud_range=point_cloud_range, 18 | voxel_size=voxel_size, 19 | max_voxels=(-1, -1))), 20 | voxel_encoder=dict( 21 | _delete_=True, 22 | type='DynamicSimpleVFE', 23 | voxel_size=voxel_size, 24 | point_cloud_range=point_cloud_range)) 25 | -------------------------------------------------------------------------------- /configs/dynamic_voxelization/second_dv_secfpn_8xb6-80e_kitti-3d-car.py: -------------------------------------------------------------------------------- 1 | _base_ = '../second/second_hv_secfpn_8xb6-80e_kitti-3d-car.py' 2 | 3 | point_cloud_range = [0, -40, -3, 70.4, 40, 1] 4 | voxel_size = [0.05, 0.05, 0.1] 5 | 6 | model = dict( 7 | type='DynamicVoxelNet', 8 | data_preprocessor=dict( 9 | voxel_type='dynamic', 10 | voxel_layer=dict( 11 | _delete_=True, 12 | max_num_points=-1, 13 | point_cloud_range=point_cloud_range, 14 | voxel_size=voxel_size, 15 | max_voxels=(-1, -1))), 16 | voxel_encoder=dict( 17 | _delete_=True, 18 | type='DynamicSimpleVFE', 19 | voxel_size=voxel_size, 20 | point_cloud_range=point_cloud_range)) 21 | -------------------------------------------------------------------------------- /configs/fcaf3d/fcaf3d_2xb8_s3dis-3d-5class.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/fcaf3d.py', '../_base_/default_runtime.py', 3 | '../_base_/datasets/s3dis-3d.py' 4 | ] 5 | 6 | model = dict(bbox_head=dict(num_classes=5)) 7 | 8 | optim_wrapper = dict( 9 | type='OptimWrapper', 10 | optimizer=dict(type='AdamW', lr=0.001, weight_decay=0.0001), 11 | clip_grad=dict(max_norm=10, norm_type=2)) 12 | 13 | # learning rate 14 | param_scheduler = dict( 15 | type='MultiStepLR', 16 | begin=0, 17 | end=12, 18 | by_epoch=True, 19 | milestones=[8, 11], 20 | gamma=0.1) 21 | 22 | custom_hooks = [dict(type='EmptyCacheHook', after_iter=True)] 23 | 24 | # training schedule for 1x 25 | train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=12) 26 | val_cfg = dict(type='ValLoop') 27 | test_cfg = dict(type='TestLoop') 28 | -------------------------------------------------------------------------------- /configs/fcos3d/fcos3d_r101-caffe-dcn_fpn_head-gn_8xb2-1x_nus-mono3d_finetune.py: -------------------------------------------------------------------------------- 1 | _base_ = './fcos3d_r101-caffe-dcn_fpn_head-gn_8xb2-1x_nus-mono3d.py' 2 | # model settings 3 | model = dict( 4 | train_cfg=dict( 5 | code_weight=[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.05, 0.05])) 6 | # optimizer 7 | optim_wrapper = dict(optimizer=dict(lr=0.001)) 8 | load_from = 'work_dirs/fcos3d_nus/latest.pth' 9 | -------------------------------------------------------------------------------- /configs/free_anchor/pointpillars_hv_regnet-1.6gf_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = './pointpillars_hv_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d.py' 2 | 3 | model = dict( 4 | pts_backbone=dict( 5 | _delete_=True, 6 | type='NoStemRegNet', 7 | arch='regnetx_1.6gf', 8 | init_cfg=dict( 9 | type='Pretrained', checkpoint='open-mmlab://regnetx_1.6gf'), 10 | out_indices=(1, 2, 3), 11 | frozen_stages=-1, 12 | strides=(1, 2, 2, 2), 13 | base_channels=64, 14 | stem_channels=64, 15 | norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01), 16 | norm_eval=False, 17 | style='pytorch'), 18 | pts_neck=dict(in_channels=[168, 408, 912])) 19 | -------------------------------------------------------------------------------- /configs/free_anchor/pointpillars_hv_regnet-3.2gf_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = './pointpillars_hv_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d.py' 2 | 3 | model = dict( 4 | pts_backbone=dict( 5 | _delete_=True, 6 | type='NoStemRegNet', 7 | arch='regnetx_3.2gf', 8 | init_cfg=dict( 9 | type='Pretrained', checkpoint='open-mmlab://regnetx_3.2gf'), 10 | out_indices=(1, 2, 3), 11 | frozen_stages=-1, 12 | strides=(1, 2, 2, 2), 13 | base_channels=64, 14 | stem_channels=64, 15 | norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01), 16 | norm_eval=False, 17 | style='pytorch'), 18 | pts_neck=dict(in_channels=[192, 432, 1008])) 19 | -------------------------------------------------------------------------------- /configs/free_anchor/pointpillars_hv_regnet-400mf_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = './pointpillars_hv_fpn_head-free-anchor_sbn-all_8xb4-2x_nus-3d.py' 2 | 3 | model = dict( 4 | pts_backbone=dict( 5 | _delete_=True, 6 | type='NoStemRegNet', 7 | arch='regnetx_400mf', 8 | init_cfg=dict( 9 | type='Pretrained', checkpoint='open-mmlab://regnetx_400mf'), 10 | out_indices=(1, 2, 3), 11 | frozen_stages=-1, 12 | strides=(1, 2, 2, 2), 13 | base_channels=64, 14 | stem_channels=64, 15 | norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01), 16 | norm_eval=False, 17 | style='pytorch'), 18 | pts_neck=dict(in_channels=[64, 160, 384])) 19 | -------------------------------------------------------------------------------- /configs/h3dnet/metafile.yml: -------------------------------------------------------------------------------- 1 | Collections: 2 | - Name: H3DNet 3 | Metadata: 4 | Training Data: ScanNet 5 | Training Techniques: 6 | - AdamW 7 | Training Resources: 8x GeForce GTX 1080 Ti 8 | Architecture: 9 | Paper: 10 | URL: https://arxiv.org/abs/2006.05682 11 | Title: 'H3DNet: 3D Object Detection Using Hybrid Geometric Primitives' 12 | README: configs/h3dnet/README.md 13 | Code: 14 | URL: https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/models/detectors/h3dnet.py#L10 15 | Version: v0.6.0 16 | 17 | Models: 18 | - Name: h3dnet_3x8_scannet-3d-18class 19 | In Collection: H3DNet 20 | Config: configs/h3dnet/h3dnet_8xb3_scannet-seg.py 21 | Metadata: 22 | Training Memory (GB): 7.9 23 | Results: 24 | - Task: 3D Object Detection 25 | Dataset: ScanNet 26 | Metrics: 27 | AP@0.25: 66.07 28 | AP@0.5: 47.68 29 | Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/h3dnet/h3dnet_3x8_scannet-3d-18class/h3dnet_3x8_scannet-3d-18class_20210824_003149-414bd304.pth 30 | -------------------------------------------------------------------------------- /configs/imvoxelnet/metafile.yml: -------------------------------------------------------------------------------- 1 | Collections: 2 | - Name: ImVoxelNet 3 | Metadata: 4 | Training Data: KITTI 5 | Training Techniques: 6 | - AdamW 7 | Training Resources: 8x Tesla P40 8 | Architecture: 9 | - Anchor3DHead 10 | Paper: 11 | URL: https://arxiv.org/abs/2106.01178 12 | Title: 'ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection' 13 | README: configs/imvoxelnet/README.md 14 | Code: 15 | URL: https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/models/detectors/imvoxelnet.py#L11 16 | Version: v0.15.0 17 | 18 | Models: 19 | - Name: imvoxelnet_kitti-3d-car 20 | In Collection: ImVoxelNet 21 | Config: configs/imvoxelnet/imvoxelnet_8xb4_kitti-3d-car.py 22 | Metadata: 23 | Training Memory (GB): 15.0 24 | Results: 25 | - Task: 3D Object Detection 26 | Dataset: KITTI 27 | Metrics: 28 | mAP: 17.26 29 | Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/imvoxelnet/imvoxelnet_4x8_kitti-3d-car/imvoxelnet_4x8_kitti-3d-car_20210830_003014-3d0ffdf4.pth 30 | -------------------------------------------------------------------------------- /configs/minkunet/minkunet18_w16_torchsparse_8xb2-amp-15e_semantickitti.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./minkunet18_w32_torchsparse_8xb2-amp-15e_semantickitti.py'] 2 | 3 | model = dict( 4 | backbone=dict( 5 | base_channels=16, 6 | encoder_channels=[16, 32, 64, 128], 7 | decoder_channels=[128, 64, 48, 48]), 8 | decode_head=dict(channels=48)) 9 | 10 | # NOTE: Due to TorchSparse backend, the model performance is relatively 11 | # dependent on random seeds, and if random seeds are not specified the 12 | # model performance will be different (± 1.5 mIoU). 13 | randomness = dict(seed=1588147245) 14 | -------------------------------------------------------------------------------- /configs/minkunet/minkunet18_w20_torchsparse_8xb2-amp-15e_semantickitti.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./minkunet18_w32_torchsparse_8xb2-amp-15e_semantickitti.py'] 2 | 3 | model = dict( 4 | backbone=dict( 5 | base_channels=20, 6 | encoder_channels=[20, 40, 81, 163], 7 | decoder_channels=[163, 81, 61, 61]), 8 | decode_head=dict(channels=61)) 9 | -------------------------------------------------------------------------------- /configs/minkunet/minkunet34_w32_minkowski_8xb2-laser-polar-mix-3x_semantickitti.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | './minkunet34_w32_torchsparse_8xb2-laser-polar-mix-3x_semantickitti.py' 3 | ] 4 | 5 | model = dict( 6 | data_preprocessor=dict(batch_first=True), 7 | backbone=dict(sparseconv_backend='minkowski')) 8 | -------------------------------------------------------------------------------- /configs/minkunet/minkunet34_w32_spconv_8xb2-amp-laser-polar-mix-3x_semantickitti.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | './minkunet34_w32_torchsparse_8xb2-laser-polar-mix-3x_semantickitti.py' 3 | ] 4 | 5 | model = dict( 6 | data_preprocessor=dict(batch_first=True), 7 | backbone=dict(sparseconv_backend='spconv')) 8 | 9 | optim_wrapper = dict(type='AmpOptimWrapper', loss_scale='dynamic') 10 | -------------------------------------------------------------------------------- /configs/minkunet/minkunet34_w32_spconv_8xb2-laser-polar-mix-3x_semantickitti.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | './minkunet34_w32_torchsparse_8xb2-laser-polar-mix-3x_semantickitti.py' 3 | ] 4 | 5 | model = dict( 6 | data_preprocessor=dict(batch_first=True), 7 | backbone=dict(sparseconv_backend='spconv')) 8 | -------------------------------------------------------------------------------- /configs/minkunet/minkunet34_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | './minkunet34_w32_torchsparse_8xb2-laser-polar-mix-3x_semantickitti.py' 3 | ] 4 | 5 | optim_wrapper = dict(type='AmpOptimWrapper', loss_scale='dynamic') 6 | -------------------------------------------------------------------------------- /configs/minkunet/minkunet34v2_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | './minkunet34_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti.py' 3 | ] 4 | 5 | model = dict( 6 | backbone=dict(type='MinkUNetBackboneV2'), 7 | decode_head=dict(channels=256 + 128 + 96)) 8 | 9 | randomness = dict(seed=None, deterministic=False, diff_rank_seed=True) 10 | env_cfg = dict(cudnn_benchmark=True) 11 | -------------------------------------------------------------------------------- /configs/monoflex/metafile.yml: -------------------------------------------------------------------------------- 1 | Collections: 2 | - Name: MonoFlex 3 | Metadata: 4 | Training Data: KITTI 5 | Training Techniques: 6 | - Adam 7 | Training Resources: 2x V100 GPUS 8 | Architecture: 9 | - MonoFlexHead 10 | - DLA 11 | Paper: 12 | URL: https://arxiv.org/abs/2104.02323 13 | Title: 'Objects are Different: Flexible Monocular 3D Object Detection' 14 | README: configs/monoflex/README.md 15 | Code: 16 | URL: https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/mmdet3d/models/detectors/monoflex.py#L7 17 | Version: v1.0.0 18 | 19 | Models: 20 | - Name: monoflex_dla34_pytorch_dlaneck_gn-all_2x4_6x_kitti-mono3d 21 | In Collection: MonoFlex 22 | Config: configs/monoflex/monoflex_dla34_pytorch_dlaneck_gn-all_2x4_6x_kitti-mono3d.py 23 | Metadata: 24 | Training Memory (GB): 9.64 25 | Results: 26 | - Task: 3D Object Detection 27 | Dataset: KITTI 28 | Metrics: 29 | mAP: 21.86 30 | Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/monoflex/monoflex_dla34_pytorch_dlaneck_gn-all_2x4_6x_kitti-mono3d_20211228_027553-d46d9bb0.pth 31 | -------------------------------------------------------------------------------- /configs/mvxnet/metafile.yml: -------------------------------------------------------------------------------- 1 | Collections: 2 | - Name: MVX-Net 3 | Metadata: 4 | Training Data: KITTI 5 | Training Techniques: 6 | - AdamW 7 | Training Resources: 8x V100 GPUs 8 | Architecture: 9 | - Feature Pyramid Network 10 | - Dynamic Voxelization 11 | Paper: 12 | URL: https://arxiv.org/abs/1904.01649 13 | Title: 'MVX-Net: Multimodal VoxelNet for 3D Object Detection' 14 | README: configs/mvxnet/README.md 15 | Code: 16 | URL: https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/models/detectors/mvx_two_stage.py#L20 17 | Version: v0.5.0 18 | 19 | Models: 20 | - Name: dv_mvx-fpn_second_secfpn_adamw_2x8_80e_kitti-3d-3class 21 | Alias: mvxnet_kitti-3class 22 | In Collection: MVX-Net 23 | Config: configs/mvxnet/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class.py 24 | Metadata: 25 | Training Memory (GB): 6.7 26 | Results: 27 | - Task: 3D Object Detection 28 | Dataset: KITTI 29 | Metrics: 30 | mAP: 63.5 31 | Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/mvxnet/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class-8963258a.pth 32 | -------------------------------------------------------------------------------- /configs/nuimages/cascade-mask-rcnn-r50-fpn_coco-20e_nuim.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade-mask-rcnn_r50_fpn_1x_nuim.py' 2 | 3 | # learning policy 4 | lr_config = dict(step=[16, 19]) 5 | runner = dict(max_epochs=20) 6 | 7 | load_from = 'http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r50_fpn_20e_coco/cascade_mask_rcnn_r50_fpn_20e_coco_bbox_mAP-0.419__segm_mAP-0.365_20200504_174711-4af8e66e.pth' # noqa 8 | -------------------------------------------------------------------------------- /configs/nuimages/cascade-mask-rcnn_r101_fpn_1x_nuim.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade-mask-rcnn_r50_fpn_1x_nuim.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/nuimages/cascade-mask-rcnn_r50_fpn_coco-20e-1x_nuim.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade-mask-rcnn_r50_fpn_1x_nuim.py' 2 | 3 | load_from = 'http://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r50_fpn_20e_coco/cascade_mask_rcnn_r50_fpn_20e_coco_bbox_mAP-0.419__segm_mAP-0.365_20200504_174711-4af8e66e.pth' # noqa 4 | -------------------------------------------------------------------------------- /configs/nuimages/cascade-mask-rcnn_x101_32x4d_fpn_1x_nuim.py: -------------------------------------------------------------------------------- 1 | _base_ = './cascade-mask-rcnn_r50_fpn_1x_nuim.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/nuimages/htc_r50_fpn_coco-20e-1x_nuim.py: -------------------------------------------------------------------------------- 1 | _base_ = './htc_r50_fpn_1x_nuim.py' 2 | 3 | load_from = 'http://download.openmmlab.com/mmdetection/v2.0/htc/htc_r50_fpn_20e_coco/htc_r50_fpn_20e_coco_20200319-fe28c577.pth' # noqa 4 | -------------------------------------------------------------------------------- /configs/nuimages/htc_r50_fpn_coco-20e_nuim.py: -------------------------------------------------------------------------------- 1 | _base_ = './htc_r50_fpn_coco-20e-1x_nuim.py' 2 | # learning policy 3 | lr_config = dict(step=[16, 19]) 4 | runner = dict(max_epochs=20) 5 | -------------------------------------------------------------------------------- /configs/nuimages/htc_x101_64x4d_fpn_dconv_c3-c5_coco-20e-1xb16_nuim.py: -------------------------------------------------------------------------------- 1 | _base_ = './htc_r50_fpn_1x_nuim.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='DCN', deform_groups=1, fallback_on_stride=False), 16 | stage_with_dcn=(False, True, True, True))) 17 | 18 | data = dict(samples_per_gpu=1, workers_per_gpu=1) 19 | # learning policy 20 | lr_config = dict(step=[16, 19]) 21 | runner = dict(max_epochs=20) 22 | 23 | load_from = 'http://download.openmmlab.com/mmdetection/v2.0/htc/htc_x101_64x4d_fpn_dconv_c3-c5_mstrain_400_1400_16x1_20e_coco/htc_x101_64x4d_fpn_dconv_c3-c5_mstrain_400_1400_16x1_20e_coco_20200312-946fd751.pth' # noqa 24 | -------------------------------------------------------------------------------- /configs/nuimages/mask-rcnn_r101_fpn_1x_nuim.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask-rcnn_r50_fpn_1x_nuim.py' 2 | model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) 3 | -------------------------------------------------------------------------------- /configs/nuimages/mask-rcnn_r50_fpn_1x_nuim.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/mask-rcnn_r50_fpn.py', 3 | '../_base_/datasets/nuim-instance.py', 4 | '../_base_/schedules/mmdet-schedule-1x.py', '../_base_/default_runtime.py' 5 | ] 6 | model = dict( 7 | roi_head=dict( 8 | bbox_head=dict(num_classes=10), mask_head=dict(num_classes=10))) 9 | -------------------------------------------------------------------------------- /configs/nuimages/mask-rcnn_r50_fpn_coco-2x_1x_nuim.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/mask-rcnn_r50_fpn.py', 3 | '../_base_/datasets/nuim-instance.py', 4 | '../_base_/schedules/mmdet-schedule-1x.py', '../_base_/default_runtime.py' 5 | ] 6 | model = dict( 7 | roi_head=dict( 8 | bbox_head=dict(num_classes=10), mask_head=dict(num_classes=10))) 9 | load_from = 'https://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_2x_coco/mask_rcnn_r50_fpn_2x_coco_bbox_mAP-0.392__segm_mAP-0.354_20200505_003907-3e542a40.pth' # noqa 10 | -------------------------------------------------------------------------------- /configs/nuimages/mask-rcnn_r50_fpn_coco-2x_1x_nus-2d.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/mask-rcnn_r50_fpn.py', 3 | '../_base_/datasets/nuim-instance.py', 4 | '../_base_/schedules/mmdet-schedule-1x.py', '../_base_/default_runtime.py' 5 | ] 6 | model = dict( 7 | roi_head=dict( 8 | bbox_head=dict(num_classes=10), mask_head=dict(num_classes=10))) 9 | 10 | backend_args = None 11 | 12 | test_pipeline = [ 13 | dict(type='LoadImageFromFile', backend_args=backend_args), 14 | dict( 15 | type='MultiScaleFlipAug', 16 | img_scale=(1600, 900), 17 | flip=False, 18 | transforms=[ 19 | dict(type='Resize', keep_ratio=True), 20 | dict(type='RandomFlip'), 21 | ]), 22 | dict( 23 | type='PackDetInputs', 24 | meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 25 | 'scale_factor')), 26 | ] 27 | data_root = 'data/nuimages/' 28 | # data = dict( 29 | # val=dict( 30 | # ann_file=data_root + 'annotations/nuimages_v1.0-mini.json'), 31 | # test=dict( 32 | # ann_file=data_root + 'annotations/nuimages_v1.0-mini.json')) 33 | -------------------------------------------------------------------------------- /configs/nuimages/mask-rcnn_x101_32x4d_fpn_1x_nuim.py: -------------------------------------------------------------------------------- 1 | _base_ = './mask-rcnn_r50_fpn_1x_nuim.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/pgd/pgd_r101-caffe_fpn_head-gn_16xb2-1x_nus-mono3d_finetune.py: -------------------------------------------------------------------------------- 1 | _base_ = './pgd_r101-caffe_fpn_head-gn_16xb2-1x_nus-mono3d.py' 2 | # model settings 3 | model = dict( 4 | train_cfg=dict(code_weight=[ 5 | 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.05, 0.05, 0.2, 0.2, 0.2, 0.2 6 | ])) 7 | # optimizer 8 | optim_wrapper = dict(optimizer=dict(lr=0.002)) 9 | load_from = 'work_dirs/pgd_nus_benchmark_1x/latest.pth' 10 | -------------------------------------------------------------------------------- /configs/pgd/pgd_r101-caffe_fpn_head-gn_16xb2-2x_nus-mono3d.py: -------------------------------------------------------------------------------- 1 | _base_ = './pgd_r101-caffe_fpn_head-gn_16xb2-1x_nus-mono3d.py' 2 | 3 | # learning policy 4 | param_scheduler = [ 5 | dict( 6 | type='LinearLR', 7 | start_factor=1.0 / 3, 8 | by_epoch=False, 9 | begin=0, 10 | end=500), 11 | dict( 12 | type='MultiStepLR', 13 | begin=0, 14 | end=24, 15 | by_epoch=True, 16 | milestones=[16, 22], 17 | gamma=0.1) 18 | ] 19 | 20 | train_cfg = dict(max_epochs=24) 21 | -------------------------------------------------------------------------------- /configs/pgd/pgd_r101-caffe_fpn_head-gn_16xb2-2x_nus-mono3d_finetune.py: -------------------------------------------------------------------------------- 1 | _base_ = './pgd_r101-caffe_fpn_head-gn_16xb2-2x_nus-mono3d.py' 2 | # model settings 3 | model = dict( 4 | train_cfg=dict(code_weight=[ 5 | 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.05, 0.05, 0.2, 0.2, 0.2, 0.2 6 | ])) 7 | # optimizer 8 | optim_wrapper = dict(optimizer=dict(lr=0.002)) 9 | load_from = 'work_dirs/pgd_nus_benchmark_2x/latest.pth' 10 | -------------------------------------------------------------------------------- /configs/point_rcnn/metafile.yml: -------------------------------------------------------------------------------- 1 | Collections: 2 | - Name: PointRCNN 3 | Metadata: 4 | Training Data: KITTI 5 | Training Techniques: 6 | - AdamW 7 | Training Resources: 8x Titan XP GPUs 8 | Architecture: 9 | - PointNet++ 10 | Paper: 11 | URL: https://arxiv.org/abs/1812.04244 12 | Title: 'PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud' 13 | README: configs/point_rcnn/README.md 14 | Code: 15 | URL: https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/mmdet3d/models/detectors/point_rcnn.py#L8 16 | Version: v1.0.0 17 | 18 | Models: 19 | - Name: point-rcnn_8xb2_kitti-3d-3class 20 | In Collection: PointRCNN 21 | Config: configs/point_rcnn/point-rcnn_8xb2_kitti-3d-3class.py 22 | Metadata: 23 | Training Memory (GB): 4.6 24 | Results: 25 | - Task: 3D Object Detection 26 | Dataset: KITTI 27 | Metrics: 28 | mAP: 70.83 29 | Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/point_rcnn/point_rcnn_2x8_kitti-3d-3classes_20211208_151344.pth 30 | -------------------------------------------------------------------------------- /configs/pointnet2/pointnet2_msg_2xb16-cosine-80e_s3dis-seg.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/datasets/s3dis-seg.py', '../_base_/models/pointnet2_msg.py', 3 | '../_base_/schedules/seg-cosine-50e.py', '../_base_/default_runtime.py' 4 | ] 5 | 6 | # model settings 7 | model = dict( 8 | backbone=dict(in_channels=9), # [xyz, rgb, normalized_xyz] 9 | decode_head=dict( 10 | num_classes=13, ignore_index=13, 11 | loss_decode=dict(class_weight=None)), # S3DIS doesn't use class_weight 12 | test_cfg=dict( 13 | num_points=4096, 14 | block_size=1.0, 15 | sample_rate=0.5, 16 | use_normalized_coord=True, 17 | batch_size=24)) 18 | 19 | # data settings 20 | train_dataloader = dict(batch_size=16) 21 | 22 | # runtime settings 23 | default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=2)) 24 | 25 | # PointNet2-MSG needs longer training time than PointNet2-SSG 26 | train_cfg = dict(by_epoch=True, max_epochs=80, val_interval=2) 27 | -------------------------------------------------------------------------------- /configs/pointnet2/pointnet2_ssg_2xb16-cosine-50e_s3dis-seg.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/datasets/s3dis-seg.py', '../_base_/models/pointnet2_ssg.py', 3 | '../_base_/schedules/seg-cosine-50e.py', '../_base_/default_runtime.py' 4 | ] 5 | 6 | # model settings 7 | model = dict( 8 | backbone=dict(in_channels=9), # [xyz, rgb, normalized_xyz] 9 | decode_head=dict( 10 | num_classes=13, ignore_index=13, 11 | loss_decode=dict(class_weight=None)), # S3DIS doesn't use class_weight 12 | test_cfg=dict( 13 | num_points=4096, 14 | block_size=1.0, 15 | sample_rate=0.5, 16 | use_normalized_coord=True, 17 | batch_size=24)) 18 | 19 | # data settings 20 | train_dataloader = dict(batch_size=16) 21 | 22 | # runtime settings 23 | default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=2)) 24 | train_cfg = dict(val_interval=2) 25 | -------------------------------------------------------------------------------- /configs/pointpillars/pointpillars_hv_fpn_sbn-all_8xb2-2x_lyft-3d-range100.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/pointpillars_hv_fpn_range100_lyft.py', 3 | '../_base_/datasets/lyft-3d-range100.py', 4 | '../_base_/schedules/schedule-2x.py', '../_base_/default_runtime.py' 5 | ] 6 | # Default setting for scaling LR automatically 7 | # - `enable` means enable scaling LR automatically 8 | # or not by default. 9 | # - `base_batch_size` = (8 GPUs) x (2 samples per GPU). 10 | auto_scale_lr = dict(enable=False, base_batch_size=16) 11 | -------------------------------------------------------------------------------- /configs/pointpillars/pointpillars_hv_fpn_sbn-all_8xb2-2x_lyft-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/pointpillars_hv_fpn_lyft.py', 3 | '../_base_/datasets/lyft-3d.py', '../_base_/schedules/schedule-2x.py', 4 | '../_base_/default_runtime.py' 5 | ] 6 | # Default setting for scaling LR automatically 7 | # - `enable` means enable scaling LR automatically 8 | # or not by default. 9 | # - `base_batch_size` = (8 GPUs) x (2 samples per GPU). 10 | auto_scale_lr = dict(enable=False, base_batch_size=16) 11 | -------------------------------------------------------------------------------- /configs/pointpillars/pointpillars_hv_fpn_sbn-all_8xb2-amp-2x_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = './pointpillars_hv_fpn_sbn-all_8xb4-2x_nus-3d.py' 2 | train_dataloader = dict(batch_size=2, num_workers=2) 3 | # schedule settings 4 | optim_wrapper = dict(type='AmpOptimWrapper', loss_scale=4096.) 5 | -------------------------------------------------------------------------------- /configs/pointpillars/pointpillars_hv_fpn_sbn-all_8xb4-2x_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/pointpillars_hv_fpn_nus.py', 3 | '../_base_/datasets/nus-3d.py', '../_base_/schedules/schedule-2x.py', 4 | '../_base_/default_runtime.py' 5 | ] 6 | 7 | # For nuScenes dataset, we usually evaluate the model at the end of training. 8 | # Since the models are trained by 24 epochs by default, we set evaluation 9 | # interval to be 24. Please change the interval accordingly if you do not 10 | # use a default schedule. 11 | train_cfg = dict(val_interval=24) 12 | -------------------------------------------------------------------------------- /configs/pointpillars/pointpillars_hv_secfpn_sbn-all_16xb2-2x_waymo-3d-3class.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/pointpillars_hv_secfpn_waymo.py', 3 | '../_base_/datasets/waymoD5-3d-3class.py', 4 | '../_base_/schedules/schedule-2x.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | 8 | # data settings 9 | train_dataloader = dict(dataset=dict(dataset=dict(load_interval=1))) 10 | # Default setting for scaling LR automatically 11 | # - `enable` means enable scaling LR automatically 12 | # or not by default. 13 | # - `base_batch_size` = (16 GPUs) x (2 samples per GPU). 14 | auto_scale_lr = dict(enable=False, base_batch_size=32) 15 | -------------------------------------------------------------------------------- /configs/pointpillars/pointpillars_hv_secfpn_sbn-all_16xb2-2x_waymoD5-3d-3class.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/pointpillars_hv_secfpn_waymo.py', 3 | '../_base_/datasets/waymoD5-3d-3class.py', 4 | '../_base_/schedules/schedule-2x.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | -------------------------------------------------------------------------------- /configs/pointpillars/pointpillars_hv_secfpn_sbn-all_8xb2-amp-2x_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = './pointpillars_hv_secfpn_sbn-all_8xb4-2x_nus-3d.py' 2 | train_dataloader = dict(batch_size=2, num_workers=2) 3 | # schedule settings 4 | optim_wrapper = dict(type='AmpOptimWrapper', loss_scale=4096.) 5 | -------------------------------------------------------------------------------- /configs/pv_rcnn/metafile.yml: -------------------------------------------------------------------------------- 1 | Collections: 2 | - Name: PV-RCNN 3 | Metadata: 4 | Training Data: KITTI 5 | Training Techniques: 6 | - AdamW 7 | Training Resources: 8x A100 GPUs 8 | Architecture: 9 | - Feature Pyramid Network 10 | Paper: 11 | URL: https://arxiv.org/abs/1912.13192 12 | Title: 'PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection' 13 | README: configs/pv_rcnn/README.md 14 | Code: 15 | URL: https://github.com/open-mmlab/mmdetection3d/blob/dev-1.x/mmdet3d/models/detectors/pv_rcnn.py#L12 16 | Version: v1.1.0rc2 17 | 18 | Models: 19 | - Name: pv_rcnn_8xb2-80e_kitti-3d-3class 20 | In Collection: PV-RCNN 21 | Config: configs/pv_rcnn/pv_rcnn_8xb2-80e_kitti-3d-3class.py 22 | Metadata: 23 | Training Memory (GB): 5.4 24 | Results: 25 | - Task: 3D Object Detection 26 | Dataset: KITTI 27 | Metrics: 28 | mAP: 72.28 29 | Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/pv_rcnn/pv_rcnn_8xb2-80e_kitti-3d-3class/pv_rcnn_8xb2-80e_kitti-3d-3class_20221117_234428-b384d22f.pth 30 | -------------------------------------------------------------------------------- /configs/regnet/pointpillars_hv_regnet-1.6gf_fpn_sbn-all_8xb4-2x_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/pointpillars_hv_fpn_nus.py', 3 | '../_base_/datasets/nus-3d.py', 4 | '../_base_/schedules/schedule-2x.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | # model settings 8 | model = dict( 9 | type='MVXFasterRCNN', 10 | pts_backbone=dict( 11 | _delete_=True, 12 | type='NoStemRegNet', 13 | arch='regnetx_1.6gf', 14 | init_cfg=dict( 15 | type='Pretrained', checkpoint='open-mmlab://regnetx_1.6gf'), 16 | out_indices=(1, 2, 3), 17 | frozen_stages=-1, 18 | strides=(1, 2, 2, 2), 19 | base_channels=64, 20 | stem_channels=64, 21 | norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01), 22 | norm_eval=False, 23 | style='pytorch'), 24 | pts_neck=dict(in_channels=[168, 408, 912])) 25 | -------------------------------------------------------------------------------- /configs/regnet/pointpillars_hv_regnet-400mf_fpn_sbn-all_8xb2-2x_lyft-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/pointpillars_hv_fpn_lyft.py', 3 | '../_base_/datasets/lyft-3d.py', 4 | '../_base_/schedules/schedule-2x.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | # model settings 8 | model = dict( 9 | type='MVXFasterRCNN', 10 | pts_backbone=dict( 11 | _delete_=True, 12 | type='NoStemRegNet', 13 | arch=dict(w0=24, wa=24.48, wm=2.54, group_w=16, depth=22, bot_mul=1.0), 14 | init_cfg=dict( 15 | type='Pretrained', checkpoint='open-mmlab://regnetx_400mf'), 16 | out_indices=(1, 2, 3), 17 | frozen_stages=-1, 18 | strides=(1, 2, 2, 2), 19 | base_channels=64, 20 | stem_channels=64, 21 | norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01), 22 | norm_eval=False, 23 | style='pytorch'), 24 | pts_neck=dict(in_channels=[64, 160, 384])) 25 | # Default setting for scaling LR automatically 26 | # - `enable` means enable scaling LR automatically 27 | # or not by default. 28 | # - `base_batch_size` = (8 GPUs) x (2 samples per GPU). 29 | auto_scale_lr = dict(enable=False, base_batch_size=16) 30 | -------------------------------------------------------------------------------- /configs/regnet/pointpillars_hv_regnet-400mf_fpn_sbn-all_8xb4-2x_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/pointpillars_hv_fpn_nus.py', 3 | '../_base_/datasets/nus-3d.py', 4 | '../_base_/schedules/schedule-2x.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | # model settings 8 | model = dict( 9 | type='MVXFasterRCNN', 10 | pts_backbone=dict( 11 | _delete_=True, 12 | type='NoStemRegNet', 13 | arch=dict(w0=24, wa=24.48, wm=2.54, group_w=16, depth=22, bot_mul=1.0), 14 | init_cfg=dict( 15 | type='Pretrained', checkpoint='open-mmlab://regnetx_400mf'), 16 | out_indices=(1, 2, 3), 17 | frozen_stages=-1, 18 | strides=(1, 2, 2, 2), 19 | base_channels=64, 20 | stem_channels=64, 21 | norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01), 22 | norm_eval=False, 23 | style='pytorch'), 24 | pts_neck=dict(in_channels=[64, 160, 384])) 25 | -------------------------------------------------------------------------------- /configs/regnet/pointpillars_hv_regnet-400mf_fpn_sbn-all_range100_8xb2-2x_lyft-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/pointpillars_hv_fpn_range100_lyft.py', 3 | '../_base_/datasets/lyft-3d-range100.py', 4 | '../_base_/schedules/schedule-2x.py', 5 | '../_base_/default_runtime.py', 6 | ] 7 | # model settings 8 | model = dict( 9 | type='MVXFasterRCNN', 10 | pts_backbone=dict( 11 | _delete_=True, 12 | type='NoStemRegNet', 13 | arch=dict(w0=24, wa=24.48, wm=2.54, group_w=16, depth=22, bot_mul=1.0), 14 | init_cfg=dict( 15 | type='Pretrained', checkpoint='open-mmlab://regnetx_400mf'), 16 | out_indices=(1, 2, 3), 17 | frozen_stages=-1, 18 | strides=(1, 2, 2, 2), 19 | base_channels=64, 20 | stem_channels=64, 21 | norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01), 22 | norm_eval=False, 23 | style='pytorch'), 24 | pts_neck=dict(in_channels=[64, 160, 384])) 25 | # Default setting for scaling LR automatically 26 | # - `enable` means enable scaling LR automatically 27 | # or not by default. 28 | # - `base_batch_size` = (8 GPUs) x (2 samples per GPU). 29 | auto_scale_lr = dict(enable=False, base_batch_size=16) 30 | -------------------------------------------------------------------------------- /configs/second/second_hv_secfpn_8xb6-80e_kitti-3d-3class.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/second_hv_secfpn_kitti.py', 3 | '../_base_/datasets/kitti-3d-3class.py', 4 | '../_base_/schedules/cyclic-40e.py', '../_base_/default_runtime.py' 5 | ] 6 | -------------------------------------------------------------------------------- /configs/second/second_hv_secfpn_8xb6-80e_kitti-3d-car.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../_base_/models/second_hv_secfpn_kitti.py', 3 | '../_base_/datasets/kitti-3d-car.py', '../_base_/schedules/cyclic-40e.py', 4 | '../_base_/default_runtime.py' 5 | ] 6 | point_cloud_range = [0, -40, -3, 70.4, 40, 1] 7 | model = dict( 8 | bbox_head=dict( 9 | type='Anchor3DHead', 10 | num_classes=1, 11 | anchor_generator=dict( 12 | _delete_=True, 13 | type='Anchor3DRangeGenerator', 14 | ranges=[[0, -40.0, -1.78, 70.4, 40.0, -1.78]], 15 | sizes=[[3.9, 1.6, 1.56]], 16 | rotations=[0, 1.57], 17 | reshape_out=True)), 18 | # model training and testing settings 19 | train_cfg=dict( 20 | _delete_=True, 21 | assigner=dict( 22 | type='Max3DIoUAssigner', 23 | iou_calculator=dict(type='BboxOverlapsNearest3D'), 24 | pos_iou_thr=0.6, 25 | neg_iou_thr=0.45, 26 | min_pos_iou=0.45, 27 | ignore_iof_thr=-1), 28 | allowed_border=0, 29 | pos_weight=-1, 30 | debug=False)) 31 | -------------------------------------------------------------------------------- /configs/second/second_hv_secfpn_8xb6-amp-80e_kitti-3d-3class.py: -------------------------------------------------------------------------------- 1 | _base_ = 'second_hv_secfpn_8xb6-80e_kitti-3d-3class.py' 2 | 3 | # schedule settings 4 | optim_wrapper = dict(type='AmpOptimWrapper', loss_scale=4096.) 5 | -------------------------------------------------------------------------------- /configs/second/second_hv_secfpn_8xb6-amp-80e_kitti-3d-car.py: -------------------------------------------------------------------------------- 1 | _base_ = 'second_hv_secfpn_8xb6-80e_kitti-3d-car.py' 2 | 3 | # schedule settings 4 | optim_wrapper = dict(type='AmpOptimWrapper', loss_scale=4096.) 5 | -------------------------------------------------------------------------------- /configs/smoke/metafile.yml: -------------------------------------------------------------------------------- 1 | Collections: 2 | - Name: SMOKE 3 | Metadata: 4 | Training Data: KITTI 5 | Training Techniques: 6 | - Adam 7 | Training Resources: 4x V100 GPUS 8 | Architecture: 9 | - SMOKEMono3DHead 10 | - DLA 11 | Paper: 12 | URL: https://arxiv.org/abs/2002.10111 13 | Title: 'SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation' 14 | README: configs/smoke/README.md 15 | Code: 16 | URL: https://github.com/open-mmlab/mmdetection3d/blob/v1.0.0.dev0/mmdet3d/models/detectors/smoke_mono3d.py#L7 17 | Version: v1.0.0 18 | 19 | Models: 20 | - Name: smoke_dla34_dlaneck_gn-all_4xb8-6x_kitti-mono3d 21 | In Collection: SMOKE 22 | Config: configs/smoke/smoke_dla34_dlaneck_gn-all_4xb8-6x_kitti-mono3d.py 23 | Metadata: 24 | Training Memory (GB): 9.6 25 | Results: 26 | - Task: 3D Object Detection 27 | Dataset: KITTI 28 | Metrics: 29 | mAP: 13.8 30 | Weights: https://download.openmmlab.com/mmdetection3d/v0.1.0_models/smoke/smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d_20210929_015553-d46d9bb0.pth 31 | -------------------------------------------------------------------------------- /configs/spvcnn/spvcnn_w16_8xb2-amp-15e_semantickitti.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./spvcnn_w32_8xb2-amp-15e_semantickitti.py'] 2 | 3 | model = dict( 4 | backbone=dict( 5 | base_channels=16, 6 | encoder_channels=[16, 32, 64, 128], 7 | decoder_channels=[128, 64, 48, 48]), 8 | decode_head=dict(channels=48)) 9 | 10 | randomness = dict(seed=1588147245) 11 | -------------------------------------------------------------------------------- /configs/spvcnn/spvcnn_w20_8xb2-amp-15e_semantickitti.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./spvcnn_w32_8xb2-amp-15e_semantickitti.py'] 2 | 3 | model = dict( 4 | backbone=dict( 5 | base_channels=20, 6 | encoder_channels=[20, 40, 81, 163], 7 | decoder_channels=[163, 81, 61, 61]), 8 | decode_head=dict(channels=61)) 9 | -------------------------------------------------------------------------------- /configs/ssn/ssn_hv_regnet-400mf_secfpn_sbn-all_16xb1-2x_lyft-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = './ssn_hv_secfpn_sbn-all_16xb2-2x_lyft-3d.py' 2 | # model settings 3 | model = dict( 4 | type='MVXFasterRCNN', 5 | pts_backbone=dict( 6 | _delete_=True, 7 | type='NoStemRegNet', 8 | arch=dict(w0=24, wa=24.48, wm=2.54, group_w=16, depth=22, bot_mul=1.0), 9 | init_cfg=dict( 10 | type='Pretrained', checkpoint='open-mmlab://regnetx_400mf'), 11 | out_indices=(1, 2, 3), 12 | frozen_stages=-1, 13 | strides=(1, 2, 2, 2), 14 | base_channels=64, 15 | stem_channels=64, 16 | norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01), 17 | norm_eval=False, 18 | style='pytorch'), 19 | pts_neck=dict(in_channels=[64, 160, 384])) 20 | # dataset settings 21 | train_dataloader = dict(batch_size=1, num_workers=2) 22 | -------------------------------------------------------------------------------- /configs/ssn/ssn_hv_regnet-400mf_secfpn_sbn-all_16xb2-2x_nus-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = './ssn_hv_secfpn_sbn-all_16xb2-2x_nus-3d.py' 2 | # model settings 3 | model = dict( 4 | type='MVXFasterRCNN', 5 | data_preprocessor=dict(type='Det3DDataPreprocessor'), 6 | pts_backbone=dict( 7 | _delete_=True, 8 | type='NoStemRegNet', 9 | arch=dict(w0=24, wa=24.48, wm=2.54, group_w=16, depth=22, bot_mul=1.0), 10 | init_cfg=dict( 11 | type='Pretrained', checkpoint='open-mmlab://regnetx_400mf'), 12 | out_indices=(1, 2, 3), 13 | frozen_stages=-1, 14 | strides=(1, 2, 2, 2), 15 | base_channels=64, 16 | stem_channels=64, 17 | norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01), 18 | norm_eval=False, 19 | style='pytorch'), 20 | pts_neck=dict(in_channels=[64, 160, 384])) 21 | -------------------------------------------------------------------------------- /configs/votenet/votenet_8xb16_sunrgbd-3d.py: -------------------------------------------------------------------------------- 1 | # TODO refactor the config of sunrgbd 2 | _base_ = [ 3 | '../_base_/datasets/sunrgbd-3d.py', '../_base_/models/votenet.py', 4 | '../_base_/schedules/schedule-3x.py', '../_base_/default_runtime.py' 5 | ] 6 | # model settings 7 | model = dict( 8 | bbox_head=dict( 9 | num_classes=10, 10 | bbox_coder=dict( 11 | type='PartialBinBasedBBoxCoder', 12 | num_sizes=10, 13 | num_dir_bins=12, 14 | with_rot=True, 15 | mean_sizes=[ 16 | [2.114256, 1.620300, 0.927272], [0.791118, 1.279516, 0.718182], 17 | [0.923508, 1.867419, 0.845495], [0.591958, 0.552978, 0.827272], 18 | [0.699104, 0.454178, 0.75625], [0.69519, 1.346299, 0.736364], 19 | [0.528526, 1.002642, 1.172878], [0.500618, 0.632163, 0.683424], 20 | [0.404671, 1.071108, 1.688889], [0.76584, 1.398258, 0.472728] 21 | ]), 22 | )) 23 | # Default setting for scaling LR automatically 24 | # - `enable` means enable scaling LR automatically 25 | # or not by default. 26 | # - `base_batch_size` = (8 GPUs) x (16 samples per GPU). 27 | auto_scale_lr = dict(enable=False, base_batch_size=128) 28 | -------------------------------------------------------------------------------- /configs/votenet/votenet_head-iouloss_8xb8_scannet-3d.py: -------------------------------------------------------------------------------- 1 | _base_ = ['./votenet_8xb8_scannet-3d.py'] 2 | 3 | # model settings, add iou loss 4 | model = dict( 5 | bbox_head=dict( 6 | iou_loss=dict( 7 | type='AxisAlignedIoULoss', reduction='sum', loss_weight=10.0 / 8 | 3.0))) 9 | -------------------------------------------------------------------------------- /data/s3dis/meta_data/class_names.txt: -------------------------------------------------------------------------------- 1 | ceiling 2 | floor 3 | wall 4 | beam 5 | column 6 | window 7 | door 8 | table 9 | chair 10 | sofa 11 | bookcase 12 | board 13 | clutter 14 | -------------------------------------------------------------------------------- /data/scannet/meta_data/scannet_means.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/data/scannet/meta_data/scannet_means.npz -------------------------------------------------------------------------------- /dataset-index.yml: -------------------------------------------------------------------------------- 1 | kitti: 2 | # The name of dataset in OpenDataLab referring to 3 | # https://opendatalab.com/KITTI_Object/cli. You can also download it 4 | # by running `odl get ${dataset}` independently 5 | dataset: KITTI_Object 6 | download_root: data 7 | data_root: data/kitti 8 | # Scripts for unzipping datasets 9 | script: tools/dataset_converters/kitti_unzip.sh 10 | 11 | nuscenes: 12 | # The name of dataset in OpenDataLab referring to 13 | # https://opendatalab.com/nuScenes/cli. You can also download it 14 | # by running `odl get ${dataset}` independently 15 | dataset: nuScenes 16 | download_root: data 17 | data_root: data/nuscenes 18 | # Scripts for unzipping datasets 19 | script: tools/dataset_converters/nuscenes_unzip.sh 20 | 21 | semantickitti: 22 | # The name of dataset in OpenDataLab referring to 23 | # https://opendatalab.com/SemanticKITTI/cli. You can also download it 24 | # by running `odl get ${dataset}` independently 25 | dataset: SemanticKITTI 26 | download_root: data 27 | data_root: data/semantickitti 28 | # Scripts for unzipping datasets 29 | script: tools/dataset_converters/semantickitti_unzip.sh 30 | -------------------------------------------------------------------------------- /demo/data/kitti/000008.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/kitti/000008.bin -------------------------------------------------------------------------------- /demo/data/kitti/000008.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/kitti/000008.pkl -------------------------------------------------------------------------------- /demo/data/kitti/000008.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/kitti/000008.png -------------------------------------------------------------------------------- /demo/data/kitti/000008.txt: -------------------------------------------------------------------------------- 1 | 721.5377 0.0 609.5593 44.85728 0.0 721.5377 172.854 0.2163791 0.0 0.0 1.0 0.002745884 0.0 0.0 0.0 1.0 2 | -------------------------------------------------------------------------------- /demo/data/nuscenes/n015-2018-07-24-11-22-45+0800.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/nuscenes/n015-2018-07-24-11-22-45+0800.pkl -------------------------------------------------------------------------------- /demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__CAM_BACK_LEFT__1532402927647423.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__CAM_BACK_LEFT__1532402927647423.jpg -------------------------------------------------------------------------------- /demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__CAM_BACK_RIGHT__1532402927627893.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__CAM_BACK_RIGHT__1532402927627893.jpg -------------------------------------------------------------------------------- /demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__CAM_BACK__1532402927637525.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__CAM_BACK__1532402927637525.jpg -------------------------------------------------------------------------------- /demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__CAM_FRONT_LEFT__1532402927604844.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__CAM_FRONT_LEFT__1532402927604844.jpg -------------------------------------------------------------------------------- /demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__CAM_FRONT_RIGHT__1532402927620339.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__CAM_FRONT_RIGHT__1532402927620339.jpg -------------------------------------------------------------------------------- /demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__CAM_FRONT__1532402927612460.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__CAM_FRONT__1532402927612460.jpg -------------------------------------------------------------------------------- /demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__LIDAR_TOP__1532402927647951.pcd.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__LIDAR_TOP__1532402927647951.pcd.bin -------------------------------------------------------------------------------- /demo/data/scannet/scene0000_00.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/scannet/scene0000_00.bin -------------------------------------------------------------------------------- /demo/data/sunrgbd/000017.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/sunrgbd/000017.bin -------------------------------------------------------------------------------- /demo/data/sunrgbd/000017.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/sunrgbd/000017.jpg -------------------------------------------------------------------------------- /demo/data/sunrgbd/sunrgbd_000017_infos.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/demo/data/sunrgbd/sunrgbd_000017_infos.pkl -------------------------------------------------------------------------------- /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/en/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/en/_static/css/readthedocs.css: -------------------------------------------------------------------------------- 1 | .header-logo { 2 | background-image: url("../image/mmdet3d-logo.png"); 3 | background-size: 182.5px 40px; 4 | height: 40px; 5 | width: 182.5px; 6 | } 7 | -------------------------------------------------------------------------------- /docs/en/_static/image/mmdet3d-logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/docs/en/_static/image/mmdet3d-logo.png -------------------------------------------------------------------------------- /docs/en/advanced_guides/datasets/index.rst: -------------------------------------------------------------------------------- 1 | .. toctree:: 2 | :maxdepth: 3 3 | 4 | kitti.md 5 | nuscenes.md 6 | lyft.md 7 | waymo.md 8 | sunrgbd.md 9 | scannet.md 10 | s3dis.md 11 | semantickitti.md 12 | -------------------------------------------------------------------------------- /docs/en/advanced_guides/index.rst: -------------------------------------------------------------------------------- 1 | Datasets 2 | ************** 3 | 4 | .. toctree:: 5 | :maxdepth: 1 6 | 7 | datasets/index.rst 8 | 9 | 10 | Supported Tasks 11 | ************** 12 | 13 | .. toctree:: 14 | :maxdepth: 1 15 | 16 | supported_tasks/index.rst 17 | 18 | 19 | Customization 20 | ************** 21 | 22 | .. toctree:: 23 | :maxdepth: 1 24 | 25 | customize_dataset.md 26 | customize_models.md 27 | customize_runtime.md 28 | -------------------------------------------------------------------------------- /docs/en/advanced_guides/supported_tasks/index.rst: -------------------------------------------------------------------------------- 1 | .. toctree:: 2 | :maxdepth: 1 3 | 4 | lidar_det3d.md 5 | vision_det3d.md 6 | lidar_sem_seg3d.md 7 | -------------------------------------------------------------------------------- /docs/en/index.rst: -------------------------------------------------------------------------------- 1 | Welcome to MMDetection3D's documentation! 2 | ========================================== 3 | 4 | .. toctree:: 5 | :maxdepth: 1 6 | :caption: Get Started 7 | 8 | get_started.md 9 | 10 | .. toctree:: 11 | :maxdepth: 2 12 | :caption: User Guides 13 | 14 | user_guides/index.rst 15 | 16 | .. toctree:: 17 | :maxdepth: 2 18 | :caption: Advanced Guides 19 | 20 | advanced_guides/index.rst 21 | 22 | .. toctree:: 23 | :maxdepth: 1 24 | :caption: Migrating from MMDetection3D 1.0 25 | 26 | migration.md 27 | 28 | .. toctree:: 29 | :maxdepth: 1 30 | :caption: API Reference 31 | 32 | api.rst 33 | 34 | .. toctree:: 35 | :maxdepth: 1 36 | :caption: Model Zoo 37 | 38 | model_zoo.md 39 | 40 | .. toctree:: 41 | :maxdepth: 1 42 | :caption: Notes 43 | 44 | notes/index.rst 45 | 46 | .. toctree:: 47 | :caption: Switch Language 48 | 49 | switch_language.md 50 | 51 | Indices and tables 52 | ================== 53 | 54 | * :ref:`genindex` 55 | * :ref:`search` 56 | -------------------------------------------------------------------------------- /docs/en/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/en/notes/index.rst: -------------------------------------------------------------------------------- 1 | .. toctree:: 2 | :maxdepth: 1 3 | 4 | benchmarks.md 5 | changelog_v1.0.x.md 6 | changelog.md 7 | compatibility.md 8 | faq.md 9 | contribution_guides.md 10 | -------------------------------------------------------------------------------- /docs/en/switch_language.md: -------------------------------------------------------------------------------- 1 | ## English 2 | 3 | ## 简体中文 4 | -------------------------------------------------------------------------------- /docs/en/user_guides/index.rst: -------------------------------------------------------------------------------- 1 | Train & Test 2 | ************** 3 | .. toctree:: 4 | :maxdepth: 1 5 | 6 | config.md 7 | coord_sys_tutorial.md 8 | dataset_prepare.md 9 | data_pipeline.md 10 | train_test.md 11 | inference.md 12 | new_data_model.md 13 | 14 | Useful Tools 15 | ************ 16 | .. toctree:: 17 | :maxdepth: 1 18 | 19 | useful_tools.md 20 | visualization.md 21 | backends_support.md 22 | model_deployment.md 23 | -------------------------------------------------------------------------------- /docs/en/user_guides/model_deployment.md: -------------------------------------------------------------------------------- 1 | # Model Deployment 2 | 3 | MMDet3D 1.1 fully relies on [MMDeploy](https://mmdeploy.readthedocs.io/) to deploy models. 4 | Please stay tuned and this document will be update soon. 5 | -------------------------------------------------------------------------------- /docs/zh_cn/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/zh_cn/_static/css/readthedocs.css: -------------------------------------------------------------------------------- 1 | .header-logo { 2 | background-image: url("../image/mmdet3d-logo.png"); 3 | background-size: 182.5px 40px; 4 | height: 40px; 5 | width: 182.5px; 6 | } 7 | -------------------------------------------------------------------------------- /docs/zh_cn/_static/image/mmdet3d-logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/docs/zh_cn/_static/image/mmdet3d-logo.png -------------------------------------------------------------------------------- /docs/zh_cn/advanced_guides/datasets/index.rst: -------------------------------------------------------------------------------- 1 | .. toctree:: 2 | :maxdepth: 3 3 | 4 | kitti.md 5 | nuscenes.md 6 | lyft.md 7 | waymo.md 8 | sunrgbd.md 9 | scannet.md 10 | s3dis.md 11 | semantickitti.md 12 | -------------------------------------------------------------------------------- /docs/zh_cn/advanced_guides/index.rst: -------------------------------------------------------------------------------- 1 | 数据集 2 | ************** 3 | 4 | .. toctree:: 5 | :maxdepth: 1 6 | 7 | datasets/index.rst 8 | 9 | 10 | 支持的任务 11 | ************** 12 | 13 | .. toctree:: 14 | :maxdepth: 1 15 | 16 | supported_tasks/index.rst 17 | 18 | 19 | 自定义项目 20 | ************** 21 | 22 | .. toctree:: 23 | :maxdepth: 1 24 | 25 | customize_dataset.md 26 | customize_models.md 27 | customize_runtime.md 28 | -------------------------------------------------------------------------------- /docs/zh_cn/advanced_guides/supported_tasks/index.rst: -------------------------------------------------------------------------------- 1 | .. toctree:: 2 | :maxdepth: 1 3 | 4 | lidar_det3d.md 5 | vision_det3d.md 6 | lidar_sem_seg3d.md 7 | -------------------------------------------------------------------------------- /docs/zh_cn/index.rst: -------------------------------------------------------------------------------- 1 | 欢迎来到 MMDetection3D 文档！ 2 | ========================================== 3 | 4 | .. toctree:: 5 | :maxdepth: 1 6 | :caption: 开始你的第一步 7 | 8 | get_started.md 9 | 10 | .. toctree:: 11 | :maxdepth: 2 12 | :caption: 使用指南 13 | 14 | user_guides/index.rst 15 | 16 | .. toctree:: 17 | :maxdepth: 2 18 | :caption: 进阶教程 19 | 20 | advanced_guides/index.rst 21 | 22 | .. toctree:: 23 | :maxdepth: 1 24 | :caption: 迁移版本 25 | 26 | migration.md 27 | 28 | .. toctree:: 29 | :maxdepth: 1 30 | :caption: 接口文档（英文） 31 | 32 | api.rst 33 | 34 | .. toctree:: 35 | :maxdepth: 1 36 | :caption: 模型仓库 37 | 38 | model_zoo.md 39 | 40 | .. toctree:: 41 | :maxdepth: 1 42 | :caption: 说明 43 | 44 | notes/index.rst 45 | 46 | .. toctree:: 47 | :caption: 语言切换 48 | 49 | switch_language.md 50 | 51 | Indices and tables 52 | ================== 53 | 54 | * :ref:`genindex` 55 | * :ref:`search` 56 | -------------------------------------------------------------------------------- /docs/zh_cn/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/zh_cn/notes/changelog.md: -------------------------------------------------------------------------------- 1 | # v1.1 变更日志 2 | -------------------------------------------------------------------------------- /docs/zh_cn/notes/changelog_v1.0.x.md: -------------------------------------------------------------------------------- 1 | # v1.0.x 变更日志 2 | -------------------------------------------------------------------------------- /docs/zh_cn/notes/compatibility.md: -------------------------------------------------------------------------------- 1 | # 兼容性 2 | -------------------------------------------------------------------------------- /docs/zh_cn/notes/index.rst: -------------------------------------------------------------------------------- 1 | .. toctree:: 2 | :maxdepth: 3 3 | 4 | benchmarks.md 5 | changelog_v1.0.x.md 6 | changelog.md 7 | compatibility.md 8 | faq.md 9 | -------------------------------------------------------------------------------- /docs/zh_cn/switch_language.md: -------------------------------------------------------------------------------- 1 | ## English 2 | 3 | ## 简体中文 4 | -------------------------------------------------------------------------------- /docs/zh_cn/user_guides/index.rst: -------------------------------------------------------------------------------- 1 | 训练和测试 2 | ************** 3 | .. toctree:: 4 | :maxdepth: 1 5 | 6 | config.md 7 | coord_sys_tutorial.md 8 | dataset_prepare.md 9 | data_pipeline.md 10 | train_test.md 11 | inference.md 12 | new_data_model.md 13 | 14 | 实用工具 15 | ************ 16 | .. toctree:: 17 | :maxdepth: 1 18 | 19 | useful_tools.md 20 | visualization.md 21 | backends_support.md 22 | model_deployment.md 23 | -------------------------------------------------------------------------------- /docs/zh_cn/user_guides/model_deployment.md: -------------------------------------------------------------------------------- 1 | # 模型部署（待更新） 2 | 3 | MMDet3D 1.1 完全基于 [MMDeploy](https://mmdeploy.readthedocs.io/) 來部署模型。 4 | 我们将在下一个版本完善这个文档。 5 | -------------------------------------------------------------------------------- /mmdet3d/apis/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .inference import (convert_SyncBN, inference_detector, 3 | inference_mono_3d_detector, 4 | inference_multi_modality_detector, inference_segmentor, 5 | init_model) 6 | from .inferencers import (Base3DInferencer, LidarDet3DInferencer, 7 | LidarSeg3DInferencer, MonoDet3DInferencer, 8 | MultiModalityDet3DInferencer) 9 | 10 | __all__ = [ 11 | 'inference_detector', 'init_model', 'inference_mono_3d_detector', 12 | 'convert_SyncBN', 'inference_multi_modality_detector', 13 | 'inference_segmentor', 'Base3DInferencer', 'MonoDet3DInferencer', 14 | 'LidarDet3DInferencer', 'LidarSeg3DInferencer', 15 | 'MultiModalityDet3DInferencer' 16 | ] 17 | -------------------------------------------------------------------------------- /mmdet3d/apis/inferencers/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .base_3d_inferencer import Base3DInferencer 3 | from .lidar_det3d_inferencer import LidarDet3DInferencer 4 | from .lidar_seg3d_inferencer import LidarSeg3DInferencer 5 | from .mono_det3d_inferencer import MonoDet3DInferencer 6 | from .multi_modality_det3d_inferencer import MultiModalityDet3DInferencer 7 | 8 | __all__ = [ 9 | 'Base3DInferencer', 'MonoDet3DInferencer', 'LidarDet3DInferencer', 10 | 'LidarSeg3DInferencer', 'MultiModalityDet3DInferencer' 11 | ] 12 | -------------------------------------------------------------------------------- /mmdet3d/configs/_base_/default_runtime.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmengine.hooks.checkpoint_hook import CheckpointHook 3 | from mmengine.hooks.iter_timer_hook import IterTimerHook 4 | from mmengine.hooks.logger_hook import LoggerHook 5 | from mmengine.hooks.param_scheduler_hook import ParamSchedulerHook 6 | from mmengine.hooks.sampler_seed_hook import DistSamplerSeedHook 7 | from mmengine.runner.log_processor import LogProcessor 8 | 9 | from mmdet3d.engine.hooks.visualization_hook import Det3DVisualizationHook 10 | 11 | default_scope = 'mmdet3d' 12 | 13 | default_hooks = dict( 14 | timer=dict(type=IterTimerHook), 15 | logger=dict(type=LoggerHook, interval=50), 16 | param_scheduler=dict(type=ParamSchedulerHook), 17 | checkpoint=dict(type=CheckpointHook, interval=-1), 18 | sampler_seed=dict(type=DistSamplerSeedHook), 19 | visualization=dict(type=Det3DVisualizationHook)) 20 | 21 | env_cfg = dict( 22 | cudnn_benchmark=False, 23 | mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), 24 | dist_cfg=dict(backend='nccl'), 25 | ) 26 | 27 | log_processor = dict(type=LogProcessor, window_size=50, by_epoch=True) 28 | 29 | log_level = 'INFO' 30 | load_from = None 31 | resume = False 32 | 33 | # TODO: support auto scaling lr 34 | -------------------------------------------------------------------------------- /mmdet3d/configs/_base_/schedules/mmdet_schedule_1x.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmengine.optim.optimizer.optimizer_wrapper import OptimWrapper 3 | from mmengine.optim.scheduler.lr_scheduler import LinearLR, MultiStepLR 4 | from mmengine.runner.loops import EpochBasedTrainLoop, TestLoop, ValLoop 5 | from torch.optim.sgd import SGD 6 | 7 | # training schedule for 1x 8 | train_cfg = dict(type=EpochBasedTrainLoop, max_epochs=12, val_interval=1) 9 | val_cfg = dict(type=ValLoop) 10 | test_cfg = dict(type=TestLoop) 11 | 12 | # learning rate 13 | param_scheduler = [ 14 | dict(type=LinearLR, start_factor=0.001, by_epoch=False, begin=0, end=500), 15 | dict( 16 | type=MultiStepLR, 17 | begin=0, 18 | end=12, 19 | by_epoch=True, 20 | milestones=[8, 11], 21 | gamma=0.1) 22 | ] 23 | 24 | # optimizer 25 | optim_wrapper = dict( 26 | type=OptimWrapper, 27 | optimizer=dict(type=SGD, lr=0.02, momentum=0.9, weight_decay=0.0001)) 28 | 29 | # Default setting for scaling LR automatically 30 | # - `enable` means enable scaling LR automatically 31 | # or not by default. 32 | # - `base_batch_size` = (8 GPUs) x (2 samples per GPU). 33 | auto_scale_lr = dict(enable=False, base_batch_size=16) 34 | -------------------------------------------------------------------------------- /mmdet3d/configs/_base_/schedules/schedule_3x.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmengine.optim.optimizer.optimizer_wrapper import OptimWrapper 3 | from mmengine.optim.scheduler.lr_scheduler import MultiStepLR 4 | from mmengine.runner.loops import EpochBasedTrainLoop, TestLoop, ValLoop 5 | from torch.optim.adamw import AdamW 6 | 7 | # optimizer 8 | # This schedule is mainly used by models on indoor dataset, 9 | # e.g., VoteNet on SUNRGBD and ScanNet 10 | lr = 0.008 # max learning rate 11 | optim_wrapper = dict( 12 | type=OptimWrapper, 13 | optimizer=dict(type=AdamW, lr=lr, weight_decay=0.01), 14 | clip_grad=dict(max_norm=10, norm_type=2), 15 | ) 16 | 17 | # training schedule for 3x 18 | train_cfg = dict(type=EpochBasedTrainLoop, max_epochs=36, val_interval=1) 19 | val_cfg = dict(type=ValLoop) 20 | test_cfg = dict(type=TestLoop) 21 | 22 | # learning rate 23 | param_scheduler = [ 24 | dict( 25 | type=MultiStepLR, 26 | begin=0, 27 | end=36, 28 | by_epoch=True, 29 | milestones=[24, 32], 30 | gamma=0.1) 31 | ] 32 | 33 | # Default setting for scaling LR automatically 34 | # - `enable` means enable scaling LR automatically 35 | # or not by default. 36 | # - `base_batch_size` = (4 GPUs) x (8 samples per GPU). 37 | auto_scale_lr = dict(enable=False, base_batch_size=32) 38 | -------------------------------------------------------------------------------- /mmdet3d/configs/_base_/schedules/seg_cosine_100e.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmengine.optim.optimizer.optimizer_wrapper import OptimWrapper 3 | from mmengine.optim.scheduler.lr_scheduler import CosineAnnealingLR 4 | from torch.optim.sgd import SGD 5 | 6 | # optimizer 7 | # This schedule is mainly used on S3DIS dataset in segmentation task 8 | optim_wrapper = dict( 9 | type=OptimWrapper, 10 | optimizer=dict(type=SGD, lr=0.1, momentum=0.9, weight_decay=0.001), 11 | clip_grad=None) 12 | 13 | param_scheduler = [ 14 | dict( 15 | type=CosineAnnealingLR, 16 | T_max=100, 17 | eta_min=1e-5, 18 | by_epoch=True, 19 | begin=0, 20 | end=100) 21 | ] 22 | 23 | # runtime settings 24 | train_cfg = dict(by_epoch=True, max_epochs=100, val_interval=1) 25 | val_cfg = dict() 26 | test_cfg = dict() 27 | 28 | # Default setting for scaling LR automatically 29 | # - `enable` means enable scaling LR automatically 30 | # or not by default. 31 | # - `base_batch_size` = (4 GPUs) x (32 samples per GPU). 32 | auto_scale_lr = dict(enable=False, base_batch_size=128) 33 | -------------------------------------------------------------------------------- /mmdet3d/configs/_base_/schedules/seg_cosine_150e.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmengine.optim.optimizer.optimizer_wrapper import OptimWrapper 3 | from mmengine.optim.scheduler.lr_scheduler import CosineAnnealingLR 4 | from torch.optim.sgd import SGD 5 | 6 | # optimizer 7 | # This schedule is mainly used on S3DIS dataset in segmentation task 8 | optim_wrapper = dict( 9 | type=OptimWrapper, 10 | optimizer=dict(type=SGD, lr=0.2, momentum=0.9, weight_decay=0.0001), 11 | clip_grad=None) 12 | 13 | param_scheduler = [ 14 | dict( 15 | type=CosineAnnealingLR, 16 | T_max=150, 17 | eta_min=0.002, 18 | by_epoch=True, 19 | begin=0, 20 | end=150) 21 | ] 22 | 23 | # runtime settings 24 | train_cfg = dict(by_epoch=True, max_epochs=150, val_interval=1) 25 | val_cfg = dict() 26 | test_cfg = dict() 27 | 28 | # Default setting for scaling LR automatically 29 | # - `enable` means enable scaling LR automatically 30 | # or not by default. 31 | # - `base_batch_size` = (8 GPUs) x (8 samples per GPU). 32 | auto_scale_lr = dict(enable=False, base_batch_size=64) 33 | -------------------------------------------------------------------------------- /mmdet3d/configs/_base_/schedules/seg_cosine_200e.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmengine.optim.optimizer.optimizer_wrapper import OptimWrapper 3 | from mmengine.optim.scheduler.lr_scheduler import CosineAnnealingLR 4 | from torch.optim.adam import Adam 5 | 6 | # optimizer 7 | # This schedule is mainly used on S3DIS dataset in segmentation task 8 | optim_wrapper = dict( 9 | type=OptimWrapper, 10 | optimizer=dict(type=Adam, lr=0.001, weight_decay=0.01), 11 | clip_grad=None) 12 | 13 | param_scheduler = [ 14 | dict( 15 | type=CosineAnnealingLR, 16 | T_max=200, 17 | eta_min=1e-5, 18 | by_epoch=True, 19 | begin=0, 20 | end=200) 21 | ] 22 | 23 | # runtime settings 24 | train_cfg = dict(by_epoch=True, max_epochs=200, val_interval=1) 25 | val_cfg = dict() 26 | test_cfg = dict() 27 | 28 | # Default setting for scaling LR automatically 29 | # - `enable` means enable scaling LR automatically 30 | # or not by default. 31 | # - `base_batch_size` = (2 GPUs) x (16 samples per GPU). 32 | auto_scale_lr = dict(enable=False, base_batch_size=32) 33 | -------------------------------------------------------------------------------- /mmdet3d/configs/_base_/schedules/seg_cosine_50e.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmengine.optim.optimizer.optimizer_wrapper import OptimWrapper 3 | from mmengine.optim.scheduler.lr_scheduler import CosineAnnealingLR 4 | from torch.optim.adam import Adam 5 | 6 | # optimizer 7 | # This schedule is mainly used on S3DIS dataset in segmentation task 8 | optim_wrapper = dict( 9 | type=OptimWrapper, 10 | optimizer=dict(type=Adam, lr=0.001, weight_decay=0.001), 11 | clip_grad=None) 12 | 13 | param_scheduler = [ 14 | dict( 15 | type=CosineAnnealingLR, 16 | T_max=50, 17 | eta_min=1e-5, 18 | by_epoch=True, 19 | begin=0, 20 | end=50) 21 | ] 22 | 23 | # runtime settings 24 | train_cfg = dict(by_epoch=True, max_epochs=50, val_interval=1) 25 | val_cfg = dict() 26 | test_cfg = dict() 27 | 28 | # Default setting for scaling LR automatically 29 | # - `enable` means enable scaling LR automatically 30 | # or not by default. 31 | # - `base_batch_size` = (2 GPUs) x (16 samples per GPU). 32 | auto_scale_lr = dict(enable=False, base_batch_size=32) 33 | -------------------------------------------------------------------------------- /mmdet3d/configs/votenet/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | -------------------------------------------------------------------------------- /mmdet3d/engine/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .hooks import BenchmarkHook, Det3DVisualizationHook 3 | 4 | __all__ = ['Det3DVisualizationHook', 'BenchmarkHook'] 5 | -------------------------------------------------------------------------------- /mmdet3d/engine/hooks/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .benchmark_hook import BenchmarkHook 3 | from .disable_object_sample_hook import DisableObjectSampleHook 4 | from .visualization_hook import Det3DVisualizationHook 5 | 6 | __all__ = [ 7 | 'Det3DVisualizationHook', 'BenchmarkHook', 'DisableObjectSampleHook' 8 | ] 9 | -------------------------------------------------------------------------------- /mmdet3d/evaluation/functional/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .indoor_eval import (average_precision, eval_det_cls, eval_map_recall, 3 | indoor_eval) 4 | from .instance_seg_eval import (aggregate_predictions, instance_seg_eval, 5 | rename_gt) 6 | from .kitti_utils import do_eval, kitti_eval, kitti_eval_coco_style 7 | from .lyft_eval import (get_classwise_aps, get_single_class_aps, load_lyft_gts, 8 | load_lyft_predictions, lyft_eval) 9 | from .panoptic_seg_eval import panoptic_seg_eval 10 | from .scannet_utils import evaluate_matches, scannet_eval 11 | from .seg_eval import fast_hist, get_acc, get_acc_cls, per_class_iou, seg_eval 12 | 13 | __all__ = [ 14 | 'average_precision', 'eval_det_cls', 'eval_map_recall', 'indoor_eval', 15 | 'aggregate_predictions', 'rename_gt', 'instance_seg_eval', 'load_lyft_gts', 16 | 'load_lyft_predictions', 'lyft_eval', 'get_classwise_aps', 17 | 'get_single_class_aps', 'fast_hist', 'per_class_iou', 'get_acc', 18 | 'get_acc_cls', 'seg_eval', 'kitti_eval', 'kitti_eval_coco_style', 19 | 'scannet_eval', 'evaluate_matches', 'do_eval', 'panoptic_seg_eval' 20 | ] 21 | -------------------------------------------------------------------------------- /mmdet3d/evaluation/functional/kitti_utils/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .eval import do_eval, eval_class, kitti_eval, kitti_eval_coco_style 3 | 4 | __all__ = ['kitti_eval', 'kitti_eval_coco_style', 'do_eval', 'eval_class'] 5 | -------------------------------------------------------------------------------- /mmdet3d/evaluation/functional/scannet_utils/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .evaluate_semantic_instance import evaluate_matches, scannet_eval 3 | 4 | __all__ = ['scannet_eval', 'evaluate_matches'] 5 | -------------------------------------------------------------------------------- /mmdet3d/evaluation/functional/waymo_utils/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | 3 | from .prediction_to_waymo import Prediction2Waymo 4 | 5 | __all__ = ['Prediction2Waymo'] 6 | -------------------------------------------------------------------------------- /mmdet3d/evaluation/metrics/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .indoor_metric import IndoorMetric # noqa: F401,F403 3 | from .instance_seg_metric import InstanceSegMetric # noqa: F401,F403 4 | from .kitti_metric import KittiMetric # noqa: F401,F403 5 | from .lyft_metric import LyftMetric # noqa: F401,F403 6 | from .nuscenes_metric import NuScenesMetric # noqa: F401,F403 7 | from .panoptic_seg_metric import PanopticSegMetric # noqa: F401,F403 8 | from .seg_metric import SegMetric # noqa: F401,F403 9 | from .waymo_metric import WaymoMetric # noqa: F401,F403 10 | 11 | __all__ = [ 12 | 'KittiMetric', 'NuScenesMetric', 'IndoorMetric', 'LyftMetric', 'SegMetric', 13 | 'InstanceSegMetric', 'WaymoMetric', 'PanopticSegMetric' 14 | ] 15 | -------------------------------------------------------------------------------- /mmdet3d/models/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmdet3d.models.layers.fusion_layers import * # noqa: F401,F403 3 | from .backbones import * # noqa: F401,F403 4 | from .data_preprocessors import * # noqa: F401,F403 5 | from .decode_heads import * # noqa: F401,F403 6 | from .dense_heads import * # noqa: F401,F403 7 | from .detectors import * # noqa: F401,F403 8 | from .layers import * # noqa: F401,F403 9 | from .losses import * # noqa: F401,F403 10 | from .middle_encoders import * # noqa: F401,F403 11 | from .necks import * # noqa: F401,F403 12 | from .roi_heads import * # noqa: F401,F403 13 | from .segmentors import * # noqa: F401,F403 14 | from .test_time_augs import * # noqa: F401,F403 15 | from .utils import * # noqa: F401,F403 16 | from .voxel_encoders import * # noqa: F401,F403 17 | -------------------------------------------------------------------------------- /mmdet3d/models/backbones/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmdet.models.backbones import SSDVGG, HRNet, ResNet, ResNetV1d, ResNeXt 3 | 4 | from .cylinder3d import Asymm3DSpconv 5 | from .dgcnn import DGCNNBackbone 6 | from .dla import DLANet 7 | from .mink_resnet import MinkResNet 8 | from .minkunet_backbone import MinkUNetBackbone 9 | from .multi_backbone import MultiBackbone 10 | from .nostem_regnet import NoStemRegNet 11 | from .pointnet2_sa_msg import PointNet2SAMSG 12 | from .pointnet2_sa_ssg import PointNet2SASSG 13 | from .second import SECOND 14 | from .spvcnn_backone import MinkUNetBackboneV2, SPVCNNBackbone 15 | 16 | __all__ = [ 17 | 'ResNet', 'ResNetV1d', 'ResNeXt', 'SSDVGG', 'HRNet', 'NoStemRegNet', 18 | 'SECOND', 'DGCNNBackbone', 'PointNet2SASSG', 'PointNet2SAMSG', 19 | 'MultiBackbone', 'DLANet', 'MinkResNet', 'Asymm3DSpconv', 20 | 'MinkUNetBackbone', 'SPVCNNBackbone', 'MinkUNetBackboneV2' 21 | ] 22 | -------------------------------------------------------------------------------- /mmdet3d/models/data_preprocessors/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .data_preprocessor import Det3DDataPreprocessor 3 | 4 | __all__ = ['Det3DDataPreprocessor'] 5 | -------------------------------------------------------------------------------- /mmdet3d/models/decode_heads/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .cylinder3d_head import Cylinder3DHead 3 | from .decode_head import Base3DDecodeHead 4 | from .dgcnn_head import DGCNNHead 5 | from .minkunet_head import MinkUNetHead 6 | from .paconv_head import PAConvHead 7 | from .pointnet2_head import PointNet2Head 8 | 9 | __all__ = [ 10 | 'PointNet2Head', 'DGCNNHead', 'PAConvHead', 'Cylinder3DHead', 11 | 'Base3DDecodeHead', 'MinkUNetHead' 12 | ] 13 | -------------------------------------------------------------------------------- /mmdet3d/models/detectors/ssd3dnet.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmdet3d.registry import MODELS 3 | from .votenet import VoteNet 4 | 5 | 6 | @MODELS.register_module() 7 | class SSD3DNet(VoteNet): 8 | """3DSSDNet model. 9 | 10 | https://arxiv.org/abs/2002.10187.pdf 11 | """ 12 | 13 | def __init__(self, 14 | backbone, 15 | bbox_head=None, 16 | train_cfg=None, 17 | test_cfg=None, 18 | init_cfg=None, 19 | **kwargs): 20 | super(SSD3DNet, self).__init__( 21 | backbone=backbone, 22 | bbox_head=bbox_head, 23 | train_cfg=train_cfg, 24 | test_cfg=test_cfg, 25 | init_cfg=init_cfg, 26 | **kwargs) 27 | -------------------------------------------------------------------------------- /mmdet3d/models/layers/dgcnn_modules/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .dgcnn_fa_module import DGCNNFAModule 3 | from .dgcnn_fp_module import DGCNNFPModule 4 | from .dgcnn_gf_module import DGCNNGFModule 5 | 6 | __all__ = ['DGCNNFAModule', 'DGCNNFPModule', 'DGCNNGFModule'] 7 | -------------------------------------------------------------------------------- /mmdet3d/models/layers/fusion_layers/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .coord_transform import (apply_3d_transformation, bbox_2d_transform, 3 | coord_2d_transform) 4 | from .point_fusion import PointFusion 5 | from .vote_fusion import VoteFusion 6 | 7 | __all__ = [ 8 | 'PointFusion', 'VoteFusion', 'apply_3d_transformation', 9 | 'bbox_2d_transform', 'coord_2d_transform' 10 | ] 11 | -------------------------------------------------------------------------------- /mmdet3d/models/layers/paconv/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .paconv import PAConv, PAConvCUDA 3 | 4 | __all__ = ['PAConv', 'PAConvCUDA'] 5 | -------------------------------------------------------------------------------- /mmdet3d/models/layers/pointnet_modules/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .builder import build_sa_module 3 | from .paconv_sa_module import (PAConvCUDASAModule, PAConvCUDASAModuleMSG, 4 | PAConvSAModule, PAConvSAModuleMSG) 5 | from .point_fp_module import PointFPModule 6 | from .point_sa_module import PointSAModule, PointSAModuleMSG 7 | from .stack_point_sa_module import StackedSAModuleMSG 8 | 9 | __all__ = [ 10 | 'build_sa_module', 'PointSAModuleMSG', 'PointSAModule', 'PointFPModule', 11 | 'PAConvSAModule', 'PAConvSAModuleMSG', 'PAConvCUDASAModule', 12 | 'PAConvCUDASAModuleMSG', 'StackedSAModuleMSG' 13 | ] 14 | -------------------------------------------------------------------------------- /mmdet3d/models/layers/spconv/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .overwrite_spconv import register_spconv2 3 | 4 | try: 5 | import spconv 6 | except ImportError: 7 | IS_SPCONV2_AVAILABLE = False 8 | else: 9 | if hasattr(spconv, '__version__') and spconv.__version__ >= '2.0.0': 10 | IS_SPCONV2_AVAILABLE = register_spconv2() 11 | else: 12 | IS_SPCONV2_AVAILABLE = False 13 | 14 | __all__ = ['IS_SPCONV2_AVAILABLE'] 15 | -------------------------------------------------------------------------------- /mmdet3d/models/layers/spconv/overwrite_spconv/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .write_spconv2 import register_spconv2 3 | 4 | __all__ = ['register_spconv2'] 5 | -------------------------------------------------------------------------------- /mmdet3d/models/layers/torchsparse/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .torchsparse_wrapper import register_torchsparse 3 | 4 | try: 5 | import torchsparse # noqa 6 | except ImportError: 7 | IS_TORCHSPARSE_AVAILABLE = False 8 | else: 9 | IS_TORCHSPARSE_AVAILABLE = register_torchsparse() 10 | 11 | __all__ = ['IS_TORCHSPARSE_AVAILABLE'] 12 | -------------------------------------------------------------------------------- /mmdet3d/models/layers/torchsparse/torchsparse_wrapper.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import torch.nn as nn 3 | from mmengine.registry import MODELS 4 | 5 | 6 | def register_torchsparse() -> bool: 7 | """This func registers torchsparse modules.""" 8 | try: 9 | from torchsparse.nn import (BatchNorm, Conv3d, GroupNorm, LeakyReLU, 10 | ReLU) 11 | from torchsparse.nn.utils import fapply 12 | from torchsparse.tensor import SparseTensor 13 | except ImportError: 14 | return False 15 | else: 16 | 17 | class SyncBatchNorm(nn.SyncBatchNorm): 18 | 19 | def forward(self, input: SparseTensor) -> SparseTensor: 20 | return fapply(input, super().forward) 21 | 22 | MODELS._register_module(Conv3d, 'TorchSparseConv3d') 23 | MODELS._register_module(BatchNorm, 'TorchSparseBN') 24 | MODELS._register_module(SyncBatchNorm, 'TorchSparseSyncBN') 25 | MODELS._register_module(GroupNorm, 'TorchSparseGN') 26 | MODELS._register_module(ReLU, 'TorchSparseReLU') 27 | MODELS._register_module(LeakyReLU, 'TorchSparseLeakyReLU') 28 | return True 29 | -------------------------------------------------------------------------------- /mmdet3d/models/losses/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmdet.models.losses import FocalLoss, SmoothL1Loss, binary_cross_entropy 3 | 4 | from .axis_aligned_iou_loss import AxisAlignedIoULoss, axis_aligned_iou_loss 5 | from .chamfer_distance import ChamferDistance, chamfer_distance 6 | from .lovasz_loss import LovaszLoss 7 | from .multibin_loss import MultiBinLoss 8 | from .paconv_regularization_loss import PAConvRegularizationLoss 9 | from .rotated_iou_loss import RotatedIoU3DLoss, rotated_iou_3d_loss 10 | from .uncertain_smooth_l1_loss import UncertainL1Loss, UncertainSmoothL1Loss 11 | 12 | __all__ = [ 13 | 'FocalLoss', 'SmoothL1Loss', 'binary_cross_entropy', 'ChamferDistance', 14 | 'chamfer_distance', 'axis_aligned_iou_loss', 'AxisAlignedIoULoss', 15 | 'PAConvRegularizationLoss', 'UncertainL1Loss', 'UncertainSmoothL1Loss', 16 | 'MultiBinLoss', 'RotatedIoU3DLoss', 'rotated_iou_3d_loss', 'LovaszLoss' 17 | ] 18 | -------------------------------------------------------------------------------- /mmdet3d/models/middle_encoders/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .pillar_scatter import PointPillarsScatter 3 | from .sparse_encoder import SparseEncoder, SparseEncoderSASSD 4 | from .sparse_unet import SparseUNet 5 | from .voxel_set_abstraction import VoxelSetAbstraction 6 | 7 | __all__ = [ 8 | 'PointPillarsScatter', 'SparseEncoder', 'SparseEncoderSASSD', 'SparseUNet', 9 | 'VoxelSetAbstraction' 10 | ] 11 | -------------------------------------------------------------------------------- /mmdet3d/models/necks/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmdet.models.necks.fpn import FPN 3 | 4 | from .dla_neck import DLANeck 5 | from .imvoxel_neck import IndoorImVoxelNeck, OutdoorImVoxelNeck 6 | from .pointnet2_fp_neck import PointNetFPNeck 7 | from .second_fpn import SECONDFPN 8 | 9 | __all__ = [ 10 | 'FPN', 'SECONDFPN', 'OutdoorImVoxelNeck', 'PointNetFPNeck', 'DLANeck', 11 | 'IndoorImVoxelNeck' 12 | ] 13 | -------------------------------------------------------------------------------- /mmdet3d/models/roi_heads/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .base_3droi_head import Base3DRoIHead 3 | from .bbox_heads import PartA2BboxHead 4 | from .h3d_roi_head import H3DRoIHead 5 | from .mask_heads import PointwiseSemanticHead, PrimitiveHead 6 | from .part_aggregation_roi_head import PartAggregationROIHead 7 | from .point_rcnn_roi_head import PointRCNNRoIHead 8 | from .pv_rcnn_roi_head import PVRCNNRoiHead 9 | from .roi_extractors import Single3DRoIAwareExtractor, SingleRoIExtractor 10 | 11 | __all__ = [ 12 | 'Base3DRoIHead', 'PartAggregationROIHead', 'PointwiseSemanticHead', 13 | 'Single3DRoIAwareExtractor', 'PartA2BboxHead', 'SingleRoIExtractor', 14 | 'H3DRoIHead', 'PrimitiveHead', 'PointRCNNRoIHead', 'PVRCNNRoiHead' 15 | ] 16 | -------------------------------------------------------------------------------- /mmdet3d/models/roi_heads/bbox_heads/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmdet.models.roi_heads.bbox_heads import (BBoxHead, ConvFCBBoxHead, 3 | DoubleConvFCBBoxHead, 4 | Shared2FCBBoxHead, 5 | Shared4Conv1FCBBoxHead) 6 | 7 | from .h3d_bbox_head import H3DBboxHead 8 | from .parta2_bbox_head import PartA2BboxHead 9 | from .point_rcnn_bbox_head import PointRCNNBboxHead 10 | from .pv_rcnn_bbox_head import PVRCNNBBoxHead 11 | 12 | __all__ = [ 13 | 'BBoxHead', 'ConvFCBBoxHead', 'Shared2FCBBoxHead', 14 | 'Shared4Conv1FCBBoxHead', 'DoubleConvFCBBoxHead', 'PartA2BboxHead', 15 | 'H3DBboxHead', 'PointRCNNBboxHead', 'PVRCNNBBoxHead' 16 | ] 17 | -------------------------------------------------------------------------------- /mmdet3d/models/roi_heads/mask_heads/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .foreground_segmentation_head import ForegroundSegmentationHead 3 | from .pointwise_semantic_head import PointwiseSemanticHead 4 | from .primitive_head import PrimitiveHead 5 | 6 | __all__ = [ 7 | 'PointwiseSemanticHead', 'PrimitiveHead', 'ForegroundSegmentationHead' 8 | ] 9 | -------------------------------------------------------------------------------- /mmdet3d/models/roi_heads/roi_extractors/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmdet.models.roi_heads.roi_extractors import SingleRoIExtractor 3 | 4 | from .batch_roigridpoint_extractor import Batch3DRoIGridExtractor 5 | from .single_roiaware_extractor import Single3DRoIAwareExtractor 6 | from .single_roipoint_extractor import Single3DRoIPointExtractor 7 | 8 | __all__ = [ 9 | 'SingleRoIExtractor', 'Single3DRoIAwareExtractor', 10 | 'Single3DRoIPointExtractor', 'Batch3DRoIGridExtractor' 11 | ] 12 | -------------------------------------------------------------------------------- /mmdet3d/models/segmentors/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .base import Base3DSegmentor 3 | from .cylinder3d import Cylinder3D 4 | from .encoder_decoder import EncoderDecoder3D 5 | from .minkunet import MinkUNet 6 | from .seg3d_tta import Seg3DTTAModel 7 | 8 | __all__ = [ 9 | 'Base3DSegmentor', 'EncoderDecoder3D', 'Cylinder3D', 'MinkUNet', 10 | 'Seg3DTTAModel' 11 | ] 12 | -------------------------------------------------------------------------------- /mmdet3d/models/task_modules/anchor/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .anchor_3d_generator import (AlignedAnchor3DRangeGenerator, 3 | AlignedAnchor3DRangeGeneratorPerCls, 4 | Anchor3DRangeGenerator) 5 | from .builder import (ANCHOR_GENERATORS, PRIOR_GENERATORS, 6 | build_anchor_generator, build_prior_generator) 7 | 8 | __all__ = [ 9 | 'AlignedAnchor3DRangeGenerator', 'Anchor3DRangeGenerator', 10 | 'build_prior_generator', 'AlignedAnchor3DRangeGeneratorPerCls', 11 | 'build_anchor_generator', 'ANCHOR_GENERATORS', 'PRIOR_GENERATORS' 12 | ] 13 | -------------------------------------------------------------------------------- /mmdet3d/models/task_modules/anchor/builder.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import warnings 3 | from typing import Any 4 | 5 | from mmdet3d.registry import TASK_UTILS 6 | from mmdet3d.utils import ConfigType 7 | 8 | PRIOR_GENERATORS = TASK_UTILS 9 | 10 | ANCHOR_GENERATORS = TASK_UTILS 11 | 12 | 13 | def build_prior_generator(cfg: ConfigType, default_args=None) -> Any: 14 | warnings.warn( 15 | '``build_prior_generator`` would be deprecated soon, please use ' 16 | '``mmdet3d.registry.TASK_UTILS.build()`` ') 17 | return TASK_UTILS.build(cfg, default_args=default_args) 18 | 19 | 20 | def build_anchor_generator(cfg: ConfigType, default_args=None) -> Any: 21 | warnings.warn( 22 | '``build_anchor_generator`` would be deprecated soon, please use ' 23 | '``mmdet3d.registry.TASK_UTILS.build()`` ') 24 | return TASK_UTILS.build(cfg, default_args=default_args) 25 | -------------------------------------------------------------------------------- /mmdet3d/models/task_modules/assigners/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .max_3d_iou_assigner import Max3DIoUAssigner 3 | 4 | __all__ = ['Max3DIoUAssigner'] 5 | -------------------------------------------------------------------------------- /mmdet3d/models/task_modules/builder.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import warnings 3 | from typing import Any 4 | 5 | from mmdet3d.registry import TASK_UTILS 6 | from mmdet3d.utils.typing_utils import ConfigType 7 | 8 | BBOX_ASSIGNERS = TASK_UTILS 9 | BBOX_SAMPLERS = TASK_UTILS 10 | BBOX_CODERS = TASK_UTILS 11 | 12 | 13 | def build_assigner(cfg: ConfigType, **default_args) -> Any: 14 | """Builder of box assigner.""" 15 | warnings.warn('``build_assigner`` would be deprecated soon, please use ' 16 | '``mmdet3d.registry.TASK_UTILS.build()`` ') 17 | return TASK_UTILS.build(cfg, default_args=default_args) 18 | 19 | 20 | def build_sampler(cfg: ConfigType, **default_args) -> Any: 21 | """Builder of box sampler.""" 22 | warnings.warn('``build_sampler`` would be deprecated soon, please use ' 23 | '``mmdet3d.registry.TASK_UTILS.build()`` ') 24 | return TASK_UTILS.build(cfg, default_args=default_args) 25 | 26 | 27 | def build_bbox_coder(cfg: ConfigType, **default_args) -> Any: 28 | """Builder of box coder.""" 29 | warnings.warn('``build_bbox_coder`` would be deprecated soon, please use ' 30 | '``mmdet3d.registry.TASK_UTILS.build()`` ') 31 | return TASK_UTILS.build(cfg, default_args=default_args) 32 | -------------------------------------------------------------------------------- /mmdet3d/models/task_modules/coders/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .anchor_free_bbox_coder import AnchorFreeBBoxCoder 3 | from .centerpoint_bbox_coders import CenterPointBBoxCoder 4 | from .delta_xyzwhlr_bbox_coder import DeltaXYZWLHRBBoxCoder 5 | from .fcos3d_bbox_coder import FCOS3DBBoxCoder 6 | from .groupfree3d_bbox_coder import GroupFree3DBBoxCoder 7 | from .monoflex_bbox_coder import MonoFlexCoder 8 | from .partial_bin_based_bbox_coder import PartialBinBasedBBoxCoder 9 | from .pgd_bbox_coder import PGDBBoxCoder 10 | from .point_xyzwhlr_bbox_coder import PointXYZWHLRBBoxCoder 11 | from .smoke_bbox_coder import SMOKECoder 12 | 13 | __all__ = [ 14 | 'DeltaXYZWLHRBBoxCoder', 'PartialBinBasedBBoxCoder', 15 | 'CenterPointBBoxCoder', 'AnchorFreeBBoxCoder', 'GroupFree3DBBoxCoder', 16 | 'PointXYZWHLRBBoxCoder', 'FCOS3DBBoxCoder', 'PGDBBoxCoder', 'SMOKECoder', 17 | 'MonoFlexCoder' 18 | ] 19 | -------------------------------------------------------------------------------- /mmdet3d/models/task_modules/samplers/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from mmdet.models.task_modules.samplers import (BaseSampler, CombinedSampler, 3 | InstanceBalancedPosSampler, 4 | IoUBalancedNegSampler, 5 | OHEMSampler, RandomSampler, 6 | SamplingResult) 7 | 8 | from .iou_neg_piecewise_sampler import IoUNegPiecewiseSampler 9 | from .pseudosample import PseudoSampler 10 | 11 | __all__ = [ 12 | 'BaseSampler', 'PseudoSampler', 'RandomSampler', 13 | 'InstanceBalancedPosSampler', 'IoUBalancedNegSampler', 'CombinedSampler', 14 | 'OHEMSampler', 'SamplingResult', 'IoUNegPiecewiseSampler' 15 | ] 16 | -------------------------------------------------------------------------------- /mmdet3d/models/task_modules/voxel/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .voxel_generator import VoxelGenerator 3 | 4 | __all__ = ['VoxelGenerator'] 5 | -------------------------------------------------------------------------------- /mmdet3d/models/test_time_augs/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .merge_augs import merge_aug_bboxes_3d 3 | 4 | __all__ = ['merge_aug_bboxes_3d'] 5 | -------------------------------------------------------------------------------- /mmdet3d/models/utils/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .add_prefix import add_prefix 3 | from .clip_sigmoid import clip_sigmoid 4 | from .edge_indices import get_edge_indices 5 | from .gaussian import (draw_heatmap_gaussian, ellip_gaussian2D, gaussian_2d, 6 | gaussian_radius, get_ellip_gaussian_2D) 7 | from .gen_keypoints import get_keypoints 8 | from .handle_objs import filter_outside_objs, handle_proj_objs 9 | 10 | __all__ = [ 11 | 'clip_sigmoid', 'get_edge_indices', 'filter_outside_objs', 12 | 'handle_proj_objs', 'get_keypoints', 'gaussian_2d', 13 | 'draw_heatmap_gaussian', 'gaussian_radius', 'get_ellip_gaussian_2D', 14 | 'ellip_gaussian2D', 'add_prefix' 15 | ] 16 | -------------------------------------------------------------------------------- /mmdet3d/models/utils/add_prefix.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | def add_prefix(inputs: dict, prefix: str) -> dict: 3 | """Add prefix for dict. 4 | 5 | Args: 6 | inputs (dict): The input dict with str keys. 7 | prefix (str): The prefix to add. 8 | 9 | Returns: 10 | 11 | dict: The dict with keys updated with ``prefix``. 12 | """ 13 | 14 | outputs = dict() 15 | for name, value in inputs.items(): 16 | outputs[f'{prefix}.{name}'] = value 17 | 18 | return outputs 19 | -------------------------------------------------------------------------------- /mmdet3d/models/utils/clip_sigmoid.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import torch 3 | from torch import Tensor 4 | 5 | 6 | def clip_sigmoid(x: Tensor, eps: float = 1e-4) -> Tensor: 7 | """Sigmoid function for input feature. 8 | 9 | Args: 10 | x (Tensor): Input feature map with the shape of [B, N, H, W]. 11 | eps (float): Lower bound of the range to be clamped to. 12 | Defaults to 1e-4. 13 | 14 | Returns: 15 | Tensor: Feature map after sigmoid. 16 | """ 17 | y = torch.clamp(x.sigmoid_(), min=eps, max=1 - eps) 18 | return y 19 | -------------------------------------------------------------------------------- /mmdet3d/models/voxel_encoders/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .pillar_encoder import DynamicPillarFeatureNet, PillarFeatureNet 3 | from .voxel_encoder import (DynamicSimpleVFE, DynamicVFE, HardSimpleVFE, 4 | HardVFE, SegVFE) 5 | 6 | __all__ = [ 7 | 'PillarFeatureNet', 'DynamicPillarFeatureNet', 'HardVFE', 'DynamicVFE', 8 | 'HardSimpleVFE', 'DynamicSimpleVFE', 'SegVFE' 9 | ] 10 | -------------------------------------------------------------------------------- /mmdet3d/structures/bbox_3d/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .base_box3d import BaseInstance3DBoxes 3 | from .box_3d_mode import Box3DMode 4 | from .cam_box3d import CameraInstance3DBoxes 5 | from .coord_3d_mode import Coord3DMode 6 | from .depth_box3d import DepthInstance3DBoxes 7 | from .lidar_box3d import LiDARInstance3DBoxes 8 | from .utils import (get_box_type, get_proj_mat_by_coord_type, limit_period, 9 | mono_cam_box2vis, points_cam2img, points_img2cam, 10 | rotation_3d_in_axis, xywhr2xyxyr) 11 | 12 | __all__ = [ 13 | 'Box3DMode', 'BaseInstance3DBoxes', 'LiDARInstance3DBoxes', 14 | 'CameraInstance3DBoxes', 'DepthInstance3DBoxes', 'xywhr2xyxyr', 15 | 'get_box_type', 'rotation_3d_in_axis', 'limit_period', 'points_cam2img', 16 | 'points_img2cam', 'Coord3DMode', 'mono_cam_box2vis', 17 | 'get_proj_mat_by_coord_type' 18 | ] 19 | -------------------------------------------------------------------------------- /mmdet3d/structures/points/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .base_points import BasePoints 3 | from .cam_points import CameraPoints 4 | from .depth_points import DepthPoints 5 | from .lidar_points import LiDARPoints 6 | 7 | __all__ = ['BasePoints', 'CameraPoints', 'DepthPoints', 'LiDARPoints'] 8 | 9 | 10 | def get_points_type(points_type: str) -> type: 11 | """Get the class of points according to coordinate type. 12 | 13 | Args: 14 | points_type (str): The type of points coordinate. The valid value are 15 | "CAMERA", "LIDAR" and "DEPTH". 16 | 17 | Returns: 18 | type: Points type. 19 | """ 20 | points_type_upper = points_type.upper() 21 | if points_type_upper == 'CAMERA': 22 | points_cls = CameraPoints 23 | elif points_type_upper == 'LIDAR': 24 | points_cls = LiDARPoints 25 | elif points_type_upper == 'DEPTH': 26 | points_cls = DepthPoints 27 | else: 28 | raise ValueError('Only "points_type" of "CAMERA", "LIDAR" and "DEPTH" ' 29 | f'are supported, got {points_type}') 30 | 31 | return points_cls 32 | -------------------------------------------------------------------------------- /mmdet3d/testing/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .data_utils import (create_data_info_after_loading, 3 | create_dummy_data_info, 4 | create_mono3d_data_info_after_loading) 5 | from .model_utils import (create_detector_inputs, get_detector_cfg, 6 | get_model_cfg, setup_seed) 7 | 8 | __all__ = [ 9 | 'create_dummy_data_info', 'create_data_info_after_loading', 10 | 'create_mono3d_data_info_after_loading', 'create_detector_inputs', 11 | 'get_detector_cfg', 'get_model_cfg', 'setup_seed' 12 | ] 13 | -------------------------------------------------------------------------------- /mmdet3d/utils/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .array_converter import ArrayConverter, array_converter 3 | from .collect_env import collect_env 4 | from .compat_cfg import compat_cfg 5 | from .misc import replace_ceph_backend 6 | from .setup_env import register_all_modules, setup_multi_processes 7 | from .typing_utils import (ConfigType, InstanceList, MultiConfig, 8 | OptConfigType, OptInstanceList, OptMultiConfig, 9 | OptSampleList, OptSamplingResultList) 10 | 11 | __all__ = [ 12 | 'collect_env', 'setup_multi_processes', 'compat_cfg', 13 | 'register_all_modules', 'array_converter', 'ArrayConverter', 'ConfigType', 14 | 'OptConfigType', 'MultiConfig', 'OptMultiConfig', 'InstanceList', 15 | 'OptInstanceList', 'OptSamplingResultList', 'replace_ceph_backend', 16 | 'OptSampleList' 17 | ] 18 | -------------------------------------------------------------------------------- /mmdet3d/utils/collect_env.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import mmdet 3 | from mmengine.utils import get_git_hash 4 | from mmengine.utils.dl_utils import collect_env as collect_base_env 5 | 6 | import mmdet3d 7 | 8 | 9 | def collect_env(): 10 | """Collect the information of the running environments.""" 11 | env_info = collect_base_env() 12 | env_info['MMDetection'] = mmdet.__version__ 13 | env_info['MMDetection3D'] = mmdet3d.__version__ + '+' + get_git_hash()[:7] 14 | from mmdet3d.models.layers.spconv import IS_SPCONV2_AVAILABLE 15 | env_info['spconv2.0'] = IS_SPCONV2_AVAILABLE 16 | 17 | return env_info 18 | 19 | 20 | if __name__ == '__main__': 21 | for name, val in collect_env().items(): 22 | print(f'{name}: {val}') 23 | -------------------------------------------------------------------------------- /mmdet3d/utils/typing_utils.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | """Collecting some commonly used type hint in MMDetection3D.""" 3 | from typing import List, Optional, Union 4 | 5 | from mmdet.models.task_modules.samplers import SamplingResult 6 | from mmengine.config import ConfigDict 7 | from mmengine.structures import InstanceData 8 | 9 | from mmdet3d.structures.det3d_data_sample import Det3DDataSample 10 | 11 | # Type hint of config data 12 | ConfigType = Union[ConfigDict, dict] 13 | OptConfigType = Optional[ConfigType] 14 | 15 | # Type hint of one or more config data 16 | MultiConfig = Union[ConfigType, List[ConfigType]] 17 | OptMultiConfig = Optional[MultiConfig] 18 | 19 | InstanceList = List[InstanceData] 20 | OptInstanceList = Optional[InstanceList] 21 | 22 | SamplingResultList = List[SamplingResult] 23 | 24 | OptSamplingResultList = Optional[SamplingResultList] 25 | SampleList = List[Det3DDataSample] 26 | OptSampleList = Optional[SampleList] 27 | -------------------------------------------------------------------------------- /mmdet3d/version.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Open-MMLab. All rights reserved. 2 | 3 | __version__ = '1.4.0' 4 | short_version = __version__ 5 | 6 | 7 | def parse_version_info(version_str: str) -> tuple: 8 | """Parse a version string into a tuple. 9 | 10 | Args: 11 | version_str (str): The version string. 12 | 13 | Returns: 14 | tuple: The version info, e.g., "1.3.0" is parsed into (1, 3, 0), and 15 | "2.0.0rc4" is parsed into (2, 0, 0, 'rc4'). 16 | """ 17 | version_info = [] 18 | for x in version_str.split('.'): 19 | if x.isdigit(): 20 | version_info.append(int(x)) 21 | elif x.find('rc') != -1: 22 | patch_version = x.split('rc') 23 | version_info.append(int(patch_version[0])) 24 | version_info.append(f'rc{patch_version[1]}') 25 | return tuple(version_info) 26 | 27 | 28 | version_info = parse_version_info(__version__) 29 | -------------------------------------------------------------------------------- /mmdet3d/visualization/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .local_visualizer import Det3DLocalVisualizer 3 | from .vis_utils import (proj_camera_bbox3d_to_img, proj_depth_bbox3d_to_img, 4 | proj_lidar_bbox3d_to_img, to_depth_mode, write_obj, 5 | write_oriented_bbox) 6 | 7 | __all__ = [ 8 | 'Det3DLocalVisualizer', 'write_obj', 'write_oriented_bbox', 9 | 'to_depth_mode', 'proj_lidar_bbox3d_to_img', 'proj_depth_bbox3d_to_img', 10 | 'proj_camera_bbox3d_to_img' 11 | ] 12 | -------------------------------------------------------------------------------- /model-index.yml: -------------------------------------------------------------------------------- 1 | Import: 2 | - configs/3dssd/metafile.yml 3 | - configs/centerpoint/metafile.yml 4 | - configs/dgcnn/metafile.yml 5 | - configs/dynamic_voxelization/metafile.yml 6 | - configs/fcos3d/metafile.yml 7 | - configs/free_anchor/metafile.yml 8 | - configs/groupfree3d/metafile.yml 9 | - configs/h3dnet/metafile.yml 10 | - configs/imvotenet/metafile.yml 11 | - configs/imvoxelnet/metafile.yml 12 | - configs/monoflex/metafile.yml 13 | - configs/mvxnet/metafile.yml 14 | - configs/nuimages/metafile.yml 15 | - configs/paconv/metafile.yml 16 | - configs/parta2/metafile.yml 17 | - configs/pgd/metafile.yml 18 | - configs/point_rcnn/metafile.yml 19 | - configs/pointnet2/metafile.yml 20 | - configs/pointpillars/metafile.yml 21 | - configs/regnet/metafile.yml 22 | - configs/second/metafile.yml 23 | - configs/smoke/metafile.yml 24 | - configs/ssn/metafile.yml 25 | - configs/votenet/metafile.yml 26 | - configs/minkunet/metafile.yml 27 | - configs/cylinder3d/metafile.yml 28 | - configs/pv_rcnn/metafile.yml 29 | - configs/fcaf3d/metafile.yml 30 | - configs/spvcnn/metafile.yml 31 | -------------------------------------------------------------------------------- /projects/BEVFusion/bevfusion/__init__.py: -------------------------------------------------------------------------------- 1 | from .bevfusion import BEVFusion 2 | from .bevfusion_necks import GeneralizedLSSFPN 3 | from .depth_lss import DepthLSSTransform, LSSTransform 4 | from .loading import BEVLoadMultiViewImageFromFiles 5 | from .sparse_encoder import BEVFusionSparseEncoder 6 | from .transformer import TransformerDecoderLayer 7 | from .transforms_3d import (BEVFusionGlobalRotScaleTrans, 8 | BEVFusionRandomFlip3D, GridMask, ImageAug3D) 9 | from .transfusion_head import ConvFuser, TransFusionHead 10 | from .utils import (BBoxBEVL1Cost, HeuristicAssigner3D, HungarianAssigner3D, 11 | IoU3DCost) 12 | 13 | __all__ = [ 14 | 'BEVFusion', 'TransFusionHead', 'ConvFuser', 'ImageAug3D', 'GridMask', 15 | 'GeneralizedLSSFPN', 'HungarianAssigner3D', 'BBoxBEVL1Cost', 'IoU3DCost', 16 | 'HeuristicAssigner3D', 'DepthLSSTransform', 'LSSTransform', 17 | 'BEVLoadMultiViewImageFromFiles', 'BEVFusionSparseEncoder', 18 | 'TransformerDecoderLayer', 'BEVFusionRandomFlip3D', 19 | 'BEVFusionGlobalRotScaleTrans' 20 | ] 21 | -------------------------------------------------------------------------------- /projects/BEVFusion/bevfusion/ops/__init__.py: -------------------------------------------------------------------------------- 1 | from .bev_pool import bev_pool 2 | from .voxel import DynamicScatter, Voxelization, dynamic_scatter, voxelization 3 | 4 | __all__ = [ 5 | 'bev_pool', 'Voxelization', 'voxelization', 'dynamic_scatter', 6 | 'DynamicScatter' 7 | ] 8 | -------------------------------------------------------------------------------- /projects/BEVFusion/bevfusion/ops/bev_pool/__init__.py: -------------------------------------------------------------------------------- 1 | from .bev_pool import bev_pool 2 | 3 | __all__ = ['bev_pool'] 4 | -------------------------------------------------------------------------------- /projects/BEVFusion/bevfusion/ops/voxel/__init__.py: -------------------------------------------------------------------------------- 1 | from .scatter_points import DynamicScatter, dynamic_scatter 2 | from .voxelize import Voxelization, voxelization 3 | 4 | __all__ = ['Voxelization', 'voxelization', 'dynamic_scatter', 'DynamicScatter'] 5 | -------------------------------------------------------------------------------- /projects/BEVFusion/bevfusion/ops/voxel/src/voxelization.cpp: -------------------------------------------------------------------------------- 1 | #include 2 | #include "voxelization.h" 3 | 4 | namespace voxelization { 5 | 6 | PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) { 7 | m.def("hard_voxelize", &hard_voxelize, "hard voxelize"); 8 | m.def("dynamic_voxelize", &dynamic_voxelize, "dynamic voxelization"); 9 | m.def("dynamic_point_to_voxel_forward", &dynamic_point_to_voxel_forward, "dynamic point to voxel forward"); 10 | m.def("dynamic_point_to_voxel_backward", &dynamic_point_to_voxel_backward, "dynamic point to voxel backward"); 11 | } 12 | 13 | } // namespace voxelization 14 | -------------------------------------------------------------------------------- /projects/CENet/cenet/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | from .boundary_loss import BoundaryLoss 3 | from .cenet_backbone import CENet 4 | from .range_image_head import RangeImageHead 5 | from .range_image_segmentor import RangeImageSegmentor 6 | from .transforms_3d import SemkittiRangeView 7 | 8 | __all__ = [ 9 | 'CENet', 'RangeImageHead', 'RangeImageSegmentor', 'SemkittiRangeView', 10 | 'BoundaryLoss' 11 | ] 12 | -------------------------------------------------------------------------------- /projects/CenterFormer/centerformer/__init__.py: -------------------------------------------------------------------------------- 1 | from .bbox_ops import nms_iou3d 2 | from .centerformer import CenterFormer 3 | from .centerformer_backbone import (DeformableDecoderRPN, 4 | MultiFrameDeformableDecoderRPN) 5 | from .centerformer_head import CenterFormerBboxHead 6 | from .losses import FastFocalLoss 7 | 8 | __all__ = [ 9 | 'CenterFormer', 'DeformableDecoderRPN', 'CenterFormerBboxHead', 10 | 'FastFocalLoss', 'nms_iou3d', 'MultiFrameDeformableDecoderRPN' 11 | ] 12 | -------------------------------------------------------------------------------- /projects/DETR3D/detr3d/__init__.py: -------------------------------------------------------------------------------- 1 | from .detr3d import DETR3D 2 | from .detr3d_head import DETR3DHead 3 | from .detr3d_transformer import (Detr3DCrossAtten, Detr3DTransformer, 4 | Detr3DTransformerDecoder) 5 | from .hungarian_assigner_3d import HungarianAssigner3D 6 | from .match_cost import BBox3DL1Cost 7 | from .nms_free_coder import NMSFreeCoder 8 | from .vovnet import VoVNet 9 | 10 | __all__ = [ 11 | 'VoVNet', 'DETR3D', 'DETR3DHead', 'Detr3DTransformer', 12 | 'Detr3DTransformerDecoder', 'Detr3DCrossAtten', 'HungarianAssigner3D', 13 | 'BBox3DL1Cost', 'NMSFreeCoder' 14 | ] 15 | -------------------------------------------------------------------------------- /projects/DETR3D/detr3d/match_cost.py: -------------------------------------------------------------------------------- 1 | from typing import Union 2 | 3 | import torch 4 | from torch import Tensor 5 | 6 | from mmdet3d.registry import TASK_UTILS 7 | 8 | 9 | @TASK_UTILS.register_module() 10 | class BBox3DL1Cost(object): 11 | """BBox3DL1Cost. 12 | 13 | Args: 14 | weight (Union[float, int]): Cost weight. Defaults to 1. 15 | """ 16 | 17 | def __init__(self, weight: Union[float, int] = 1.): 18 | self.weight = weight 19 | 20 | def __call__(self, bbox_pred: Tensor, gt_bboxes: Tensor) -> Tensor: 21 | """Compute match cost. 22 | 23 | Args: 24 | bbox_pred (Tensor): Predicted boxes with normalized coordinates 25 | (cx,cy,l,w,cz,h,sin(φ),cos(φ),v_x,v_y) 26 | which are all in range [0, 1] and shape [num_query, 10]. 27 | gt_bboxes (Tensor): Ground truth boxes with `normalized` 28 | coordinates (cx,cy,l,w,cz,h,sin(φ),cos(φ),v_x,v_y). 29 | Shape [num_gt, 10]. 30 | Returns: 31 | Tensor: Match Cost matrix of shape (num_preds, num_gts). 32 | """ 33 | bbox_cost = torch.cdist(bbox_pred, gt_bboxes, p=1) 34 | return bbox_cost * self.weight 35 | -------------------------------------------------------------------------------- /projects/DETR3D/old_detr3d_converter.py: -------------------------------------------------------------------------------- 1 | from argparse import ArgumentParser 2 | 3 | import torch 4 | 5 | parser = ArgumentParser() 6 | parser.add_argument('src', default='old.pth') 7 | parser.add_argument('dst', default='new.pth') # ('training','validation') 8 | parser.add_argument('--code_size', type=int, default='10') 9 | args = parser.parse_args() 10 | model = torch.load(args.src) 11 | code_size = args.code_size 12 | if model['meta'].get('detr3d_convert_tag') is not None: 13 | print('this model has already converted!') 14 | else: 15 | print('converting...') 16 | # (cx, cy, w, l, cz, h, sin(φ), cos(φ), vx, vy) 17 | for key in model['state_dict']: 18 | tsr = model['state_dict'][key] 19 | if 'reg_branches' in key and tsr.shape[0] == code_size: 20 | print(key, ' with ', tsr.shape, 'has changed') 21 | tsr[[2, 3], ...] = tsr[[3, 2], ...] 22 | tsr[[6, 7], ...] = -tsr[[7, 6], ...] 23 | model['meta']['detr3d_convert_tag'] = True 24 | torch.save(model, args.dst) 25 | print('done...') 26 | -------------------------------------------------------------------------------- /projects/DSVT/dsvt/__init__.py: -------------------------------------------------------------------------------- 1 | from .disable_aug_hook import DisableAugHook 2 | from .dsvt import DSVT 3 | from .dsvt_head import DSVTCenterHead 4 | from .dsvt_transformer import DSVTMiddleEncoder 5 | from .dynamic_pillar_vfe import DynamicPillarVFE3D 6 | from .map2bev import PointPillarsScatter3D 7 | from .res_second import ResSECOND 8 | from .transforms_3d import ObjectRangeFilter3D, PointsRangeFilter3D 9 | from .utils import DSVTBBoxCoder 10 | 11 | __all__ = [ 12 | 'DSVTCenterHead', 'DSVT', 'DSVTMiddleEncoder', 'DynamicPillarVFE3D', 13 | 'PointPillarsScatter3D', 'ResSECOND', 'DSVTBBoxCoder', 14 | 'ObjectRangeFilter3D', 'PointsRangeFilter3D', 'DisableAugHook' 15 | ] 16 | -------------------------------------------------------------------------------- /projects/DSVT/dsvt/ops/ingroup_inds/ingroup_inds_op.py: -------------------------------------------------------------------------------- 1 | import torch 2 | from torch.autograd import Function 3 | 4 | try: 5 | from . import ingroup_inds_cuda 6 | 7 | # import ingroup_indices 8 | except ImportError: 9 | ingroup_indices = None 10 | print('Can not import ingroup indices') 11 | 12 | ingroup_indices = ingroup_inds_cuda 13 | 14 | 15 | class IngroupIndicesFunction(Function): 16 | 17 | @staticmethod 18 | def forward(ctx, group_inds): 19 | 20 | out_inds = torch.zeros_like(group_inds) - 1 21 | 22 | ingroup_indices.forward(group_inds, out_inds) 23 | 24 | ctx.mark_non_differentiable(out_inds) 25 | 26 | return out_inds 27 | 28 | @staticmethod 29 | def backward(ctx, g): 30 | 31 | return None 32 | 33 | 34 | ingroup_inds = IngroupIndicesFunction.apply 35 | -------------------------------------------------------------------------------- /projects/DSVT/dsvt/ops/ingroup_inds/src/error.cuh: -------------------------------------------------------------------------------- 1 | #pragma once 2 | #include 3 | 4 | #define CHECK_CALL(call) \ 5 | do \ 6 | { \ 7 | const cudaError_t error_code = call; \ 8 | if (error_code != cudaSuccess) \ 9 | { \ 10 | printf("CUDA Error:\n"); \ 11 | printf(" File: %s\n", __FILE__); \ 12 | printf(" Line: %d\n", __LINE__); \ 13 | printf(" Error code: %d\n", error_code); \ 14 | printf(" Error text: %s\n", \ 15 | cudaGetErrorString(error_code)); \ 16 | exit(1); \ 17 | } \ 18 | } while (0) 19 | -------------------------------------------------------------------------------- /projects/NeRF-Det/nerfdet/__init__.py: -------------------------------------------------------------------------------- 1 | from .data_preprocessor import NeRFDetDataPreprocessor 2 | from .formating import PackNeRFDetInputs 3 | from .multiview_pipeline import MultiViewPipeline, RandomShiftOrigin 4 | from .nerfdet import NerfDet 5 | from .nerfdet_head import NerfDetHead 6 | from .scannet_multiview_dataset import MultiViewScanNetDataset 7 | 8 | __all__ = [ 9 | 'MultiViewScanNetDataset', 'MultiViewPipeline', 'RandomShiftOrigin', 10 | 'PackNeRFDetInputs', 'NeRFDetDataPreprocessor', 'NerfDetHead', 'NerfDet' 11 | ] 12 | -------------------------------------------------------------------------------- /projects/PETR/petr/__init__.py: -------------------------------------------------------------------------------- 1 | from .cp_fpn import CPFPN 2 | from .hungarian_assigner_3d import HungarianAssigner3D 3 | from .match_cost import BBox3DL1Cost 4 | from .nms_free_coder import NMSFreeCoder 5 | from .petr import PETR 6 | from .petr_head import PETRHead 7 | from .petr_transformer import (PETRDNTransformer, PETRMultiheadAttention, 8 | PETRTransformer, PETRTransformerDecoder, 9 | PETRTransformerDecoderLayer, 10 | PETRTransformerEncoder) 11 | from .positional_encoding import (LearnedPositionalEncoding3D, 12 | SinePositionalEncoding3D) 13 | from .transforms_3d import GlobalRotScaleTransImage, ResizeCropFlipImage 14 | from .utils import denormalize_bbox, normalize_bbox 15 | from .vovnetcp import VoVNetCP 16 | 17 | __all__ = [ 18 | 'GlobalRotScaleTransImage', 'ResizeCropFlipImage', 'VoVNetCP', 'PETRHead', 19 | 'CPFPN', 'HungarianAssigner3D', 'NMSFreeCoder', 'BBox3DL1Cost', 20 | 'LearnedPositionalEncoding3D', 'PETRDNTransformer', 21 | 'PETRMultiheadAttention', 'PETRTransformer', 'PETRTransformerDecoder', 22 | 'PETRTransformerDecoderLayer', 'PETRTransformerEncoder', 'PETR', 23 | 'SinePositionalEncoding3D', 'denormalize_bbox', 'normalize_bbox' 24 | ] 25 | -------------------------------------------------------------------------------- /projects/TPVFormer/tpvformer/__init__.py: -------------------------------------------------------------------------------- 1 | from .cross_view_hybrid_attention import TPVCrossViewHybridAttention 2 | from .data_preprocessor import TPVFormerDataPreprocessor 3 | from .image_cross_attention import TPVImageCrossAttention 4 | from .loading import BEVLoadMultiViewImageFromFiles, SegLabelMapping 5 | from .nuscenes_dataset import NuScenesSegDataset 6 | from .positional_encoding import TPVFormerPositionalEncoding 7 | from .tpvformer import TPVFormer 8 | from .tpvformer_encoder import TPVFormerEncoder 9 | from .tpvformer_head import TPVFormerDecoder 10 | from .tpvformer_layer import TPVFormerLayer 11 | 12 | __all__ = [ 13 | 'TPVCrossViewHybridAttention', 'TPVImageCrossAttention', 14 | 'TPVFormerPositionalEncoding', 'TPVFormer', 'TPVFormerEncoder', 15 | 'TPVFormerLayer', 'NuScenesSegDataset', 'BEVLoadMultiViewImageFromFiles', 16 | 'SegLabelMapping', 'TPVFormerDecoder', 'TPVFormerDataPreprocessor' 17 | ] 18 | -------------------------------------------------------------------------------- /projects/TR3D/tr3d/__init__.py: -------------------------------------------------------------------------------- 1 | from .axis_aligned_iou_loss import TR3DAxisAlignedIoULoss 2 | from .mink_resnet import TR3DMinkResNet 3 | from .rotated_iou_loss import TR3DRotatedIoU3DLoss 4 | from .tr3d_head import TR3DHead 5 | from .tr3d_neck import TR3DNeck 6 | from .transforms_3d import TR3DPointSample 7 | 8 | __all__ = [ 9 | 'TR3DAxisAlignedIoULoss', 'TR3DMinkResNet', 'TR3DRotatedIoU3DLoss', 10 | 'TR3DHead', 'TR3DNeck', 'TR3DPointSample' 11 | ] 12 | -------------------------------------------------------------------------------- /projects/example_project/configs/fcos3d_dummy-resnet-caffe-dcn_fpn_head-gn_8xb2-1x_nus-mono3d.py: -------------------------------------------------------------------------------- 1 | _base_ = [ 2 | '../../../configs/fcos3d/fcos3d_r101-caffe-dcn_fpn_head-gn_8xb2-1x_nus-mono3d.py' # noqa 3 | ] 4 | 5 | custom_imports = dict(imports=['projects.example_project.dummy']) 6 | 7 | _base_.model.backbone.type = 'DummyResNet' 8 | -------------------------------------------------------------------------------- /projects/example_project/dummy/__init__.py: -------------------------------------------------------------------------------- 1 | from .dummy_resnet import DummyResNet 2 | 3 | __all__ = ['DummyResNet'] 4 | -------------------------------------------------------------------------------- /projects/example_project/dummy/dummy_resnet.py: -------------------------------------------------------------------------------- 1 | from mmdet.models.backbones import ResNet 2 | 3 | from mmdet3d.registry import MODELS 4 | 5 | 6 | @MODELS.register_module() 7 | class DummyResNet(ResNet): 8 | """Implements a dummy ResNet wrapper for demonstration purpose. 9 | Args: 10 | **kwargs: All the arguments are passed to the parent class. 11 | """ 12 | 13 | def __init__(self, **kwargs) -> None: 14 | print('Hello world!') 15 | super().__init__(**kwargs) 16 | -------------------------------------------------------------------------------- /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: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/requirements/build.txt -------------------------------------------------------------------------------- /requirements/docs.txt: -------------------------------------------------------------------------------- 1 | docutils==0.16.0 2 | markdown>=3.4.0 3 | myst-parser 4 | -e git+https://github.com/open-mmlab/pytorch_sphinx_theme.git#egg=pytorch_sphinx_theme 5 | sphinx==4.0.2 6 | sphinx-tabs 7 | sphinx_copybutton 8 | sphinx_markdown_tables>=0.0.16 9 | tabulate 10 | urllib3<2.0.0 11 | -------------------------------------------------------------------------------- /requirements/mminstall.txt: -------------------------------------------------------------------------------- 1 | mmcv>=2.0.0rc4,<2.2.0 2 | mmdet>=3.0.0,<3.3.0 3 | mmengine>=0.7.1,<1.0.0 4 | -------------------------------------------------------------------------------- /requirements/optional.txt: -------------------------------------------------------------------------------- 1 | black==20.8b1 # be compatible with typing-extensions 3.7.4 2 | typing-extensions # required by tensorflow<=2.6 3 | waymo-open-dataset-tf-2-6-0 # requires python>=3.7 4 | -------------------------------------------------------------------------------- /requirements/readthedocs.txt: -------------------------------------------------------------------------------- 1 | mmcv>=2.0.0rc4 2 | mmdet>=3.0.0 3 | mmengine>=0.7.1 4 | torch 5 | torchvision 6 | -------------------------------------------------------------------------------- /requirements/runtime.txt: -------------------------------------------------------------------------------- 1 | lyft_dataset_sdk 2 | networkx>=2.5 3 | numba # you should install numba==0.53.0 if your environment is cuda-9.0 4 | numpy 5 | nuscenes-devkit 6 | open3d 7 | plyfile 8 | scikit-image 9 | # by default we also use tensorboard to log results 10 | tensorboard 11 | trimesh 12 | -------------------------------------------------------------------------------- /requirements/tests.txt: -------------------------------------------------------------------------------- 1 | codecov 2 | flake8 3 | interrogate 4 | isort 5 | # Note: used for kwarray.group_items, this may be ported to mmcv in the future. 6 | kwarray 7 | parameterized 8 | pytest 9 | pytest-cov 10 | pytest-runner 11 | ubelt 12 | xdoctest >= 0.10.0 13 | yapf 14 | -------------------------------------------------------------------------------- /resources/browse_dataset_mono.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/resources/browse_dataset_mono.png -------------------------------------------------------------------------------- /resources/browse_dataset_multi_modality.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/resources/browse_dataset_multi_modality.png -------------------------------------------------------------------------------- /resources/browse_dataset_seg.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/resources/browse_dataset_seg.png -------------------------------------------------------------------------------- /resources/coord_sys_all.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/resources/coord_sys_all.png -------------------------------------------------------------------------------- /resources/data_pipeline.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/resources/data_pipeline.png -------------------------------------------------------------------------------- /resources/loss_curve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/resources/loss_curve.png -------------------------------------------------------------------------------- /resources/mmdet3d-logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/resources/mmdet3d-logo.png -------------------------------------------------------------------------------- /resources/mmdet3d_outdoor_demo.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/resources/mmdet3d_outdoor_demo.gif -------------------------------------------------------------------------------- /resources/nuimages_demo.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/resources/nuimages_demo.gif -------------------------------------------------------------------------------- /resources/open3d_visual.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/resources/open3d_visual.gif -------------------------------------------------------------------------------- /resources/open3d_visual.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/resources/open3d_visual.png -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- 1 | [yapf] 2 | BASED_ON_STYLE = pep8 3 | BLANK_LINE_BEFORE_NESTED_CLASS_OR_DEF = true 4 | SPLIT_BEFORE_EXPRESSION_AFTER_OPENING_PAREN = true 5 | 6 | [isort] 7 | line_length = 79 8 | multi_line_output = 0 9 | extra_standard_library = setuptools 10 | known_first_party = mmdet3d 11 | known_third_party = cv2,imageio,indoor3d_util,load_scannet_data,lyft_dataset_sdk,m2r,matplotlib,mmcv,mmdet,mmengine,nuimages,numba,numpy,nuscenes,pandas,plyfile,pycocotools,pyquaternion,pytest,pytorch_sphinx_theme,recommonmark,requests,scannet_utils,scipy,seaborn,shapely,skimage,sphinx,tensorflow,terminaltables,torch,trimesh,ts,waymo_open_dataset 12 | no_lines_before = STDLIB,LOCALFOLDER 13 | default_section = THIRDPARTY 14 | 15 | [codespell] 16 | ignore-words-list = ans,refridgerator,crate,hist,formating,dout,wan,nd,fo,avod,AVOD,warmup 17 | 18 | [flake8] 19 | per-file-ignores = mmdet3d/configs/*:F401,F403,F405 20 | -------------------------------------------------------------------------------- /tests/data/kitti/a.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/kitti/a.bin -------------------------------------------------------------------------------- /tests/data/kitti/kitti_dbinfos_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/kitti/kitti_dbinfos_train.pkl -------------------------------------------------------------------------------- /tests/data/kitti/kitti_gt_database/0_Pedestrian_0.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/kitti/kitti_gt_database/0_Pedestrian_0.bin -------------------------------------------------------------------------------- /tests/data/kitti/kitti_infos_mono3d.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/kitti/kitti_infos_mono3d.pkl -------------------------------------------------------------------------------- /tests/data/kitti/kitti_infos_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/kitti/kitti_infos_train.pkl -------------------------------------------------------------------------------- /tests/data/kitti/mono3d_sample_results.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/kitti/mono3d_sample_results.pkl -------------------------------------------------------------------------------- /tests/data/kitti/mono3d_sample_results2d.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/kitti/mono3d_sample_results2d.pkl -------------------------------------------------------------------------------- /tests/data/kitti/training/calib/000000.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/kitti/training/calib/000000.pkl -------------------------------------------------------------------------------- /tests/data/kitti/training/image_2/000000.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/kitti/training/image_2/000000.png -------------------------------------------------------------------------------- /tests/data/kitti/training/image_2/000007.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/kitti/training/image_2/000007.png -------------------------------------------------------------------------------- /tests/data/kitti/training/velodyne/000000.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/kitti/training/velodyne/000000.bin -------------------------------------------------------------------------------- /tests/data/kitti/training/velodyne_reduced/000000.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/kitti/training/velodyne_reduced/000000.bin -------------------------------------------------------------------------------- /tests/data/lyft/lidar/host-a017_lidar1_1236118886501000046.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/lyft/lidar/host-a017_lidar1_1236118886501000046.bin -------------------------------------------------------------------------------- /tests/data/lyft/lidar/host-a017_lidar1_1236118886701083686.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/lyft/lidar/host-a017_lidar1_1236118886701083686.bin -------------------------------------------------------------------------------- /tests/data/lyft/lidar/host-a017_lidar1_1236118886901125926.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/lyft/lidar/host-a017_lidar1_1236118886901125926.bin -------------------------------------------------------------------------------- /tests/data/lyft/lyft_infos.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/lyft/lyft_infos.pkl -------------------------------------------------------------------------------- /tests/data/lyft/lyft_infos_val.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/lyft/lyft_infos_val.pkl -------------------------------------------------------------------------------- /tests/data/lyft/sample_results.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/lyft/sample_results.pkl -------------------------------------------------------------------------------- /tests/data/lyft/v1.01-train/maps/map_raster_palo_alto.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/lyft/v1.01-train/maps/map_raster_palo_alto.png -------------------------------------------------------------------------------- /tests/data/lyft/v1.01-train/v1.01-train/category.json: -------------------------------------------------------------------------------- 1 | [{"description": "", "token": "8eccddb83fa7f8f992b2500f2ad658f65c9095588f3bc0ae338d97aff2dbcb9c", "name": "car"}, {"description": "", "token": "73e8de69959eb9f5b4cd2859e74bec4b5491417336cad63f27e8edb8530ffbf8", "name": "pedestrian"}, {"description": "", "token": "f81f51e1897311b55c0c6247c3db825466733e08df687c0ea830b026316a1c12", "name": "animal"}, {"description": "", "token": "a8619a81f5acc7da2a2f034420db2b2f43a015c8c689822e5295b5d6f7a5d8d6", "name": "other_vehicle"}, {"description": "", "token": "7ea5868735dc408109bfa74fd139bd8c5aa3767b52e054b8e792cabcf309c6f4", "name": "bus"}, {"description": "", "token": "1248d937c7a1a2eb1022ba9e806ebd5183b6c20c7f5703d8a7320600f1caad27", "name": "motorcycle"}, {"description": "", "token": "8af78d27e148a8f544f4c86b2a3f4bd6192b975d1065dd932ebdb8879778e275", "name": "truck"}, {"token": "c4e92c2b854fb03382838643c36d01a349f5624a11f184042d91d916d19acdbd", "description": "", "name": "emergency_vehicle"}, {"description": "", "token": "8c07dfa7af0da0191d59a2db50dc26ad1528be1fad483f17e2586309482d81bd", "name": "bicycle"}] 2 | -------------------------------------------------------------------------------- /tests/data/lyft/v1.01-train/v1.01-train/log.json: -------------------------------------------------------------------------------- 1 | [{"date_captured": "2019-05-01", "location": "Palo Alto", "token": "9d0166ccd4af9c089738587f6e3d21cd9c8b6102787427da8c3b4f64161160c5", "vehicle": "a101", "logfile": ""}] 2 | -------------------------------------------------------------------------------- /tests/data/lyft/v1.01-train/v1.01-train/map.json: -------------------------------------------------------------------------------- 1 | [{"log_tokens": ["9d0166ccd4af9c089738587f6e3d21cd9c8b6102787427da8c3b4f64161160c5"], "token": "53992ee3023e5494b90c316c183be829", "filename": "maps/map_raster_palo_alto.png", "category": "semantic_prior"}] 2 | -------------------------------------------------------------------------------- /tests/data/lyft/v1.01-train/v1.01-train/sample.json: -------------------------------------------------------------------------------- 1 | [{"next": "b8625b49ee4b7679cb81c50895bb918c98800c274e1bca22cd3208770bd3aaa1", "prev": "da683bff4f51b8073ef139476f5ad745711527a7bc7d83b20fcb871f32f9eda6", "token": "199e3146d98e6a2047bafbc222b92f5b67c4640a69b0d1d35b710242de816679", "scene_token": "9d0166ccd4af9c089738587f6e3d21cd9c8b6102787427da8c3b4f64161160c5", "timestamp": 1556675185903083.2}] 2 | -------------------------------------------------------------------------------- /tests/data/lyft/v1.01-train/v1.01-train/scene.json: -------------------------------------------------------------------------------- 1 | [{"description": "", "log_token": "9d0166ccd4af9c089738587f6e3d21cd9c8b6102787427da8c3b4f64161160c5", "name": "host-a101-lidar0-1240710366399037786-1240710391298976894", "first_sample_token": "0ebe3320a4049a1efe2af53c2094d102971a6269b70a72e127eaeabcbff9445d", "last_sample_token": "154956ad6f00a7c5e7058da67cca30b130ba0f3ea27dab72cd2ee802fa1f58cb", "nbr_samples": 126, "token": "9d0166ccd4af9c089738587f6e3d21cd9c8b6102787427da8c3b4f64161160c5"}] 2 | -------------------------------------------------------------------------------- /tests/data/lyft/v1.01-train/v1.01-train/sensor.json: -------------------------------------------------------------------------------- 1 | [{"modality": "camera", "channel": "CAM_FRONT_LEFT", "token": "f7dad6bb70cb8e6245f96e5537e382848335872e6e259218b0a80cc071d162c4"}, {"modality": "lidar", "channel": "LIDAR_FRONT_LEFT", "token": "629da739ea3a0814b9d79ffc3b99cdbc8bdbb6f97abf139f1ad33bd12f8fa94d"}, {"modality": "camera", "channel": "CAM_FRONT", "token": "eb9e8f60a3d6e3328d7512b9f8e6800127fe91f4d62bc8e48a0e6a7cb116cc60"}, {"modality": "lidar", "channel": "LIDAR_TOP", "token": "25bf751d7e35f295393d8a418731474b21c1f702e878c4553f112397caa48c08"}, {"modality": "camera", "channel": "CAM_BACK_LEFT", "token": "c84592e22beb2c0f14d5159245ce8d6678431b879e940eed580651c09cc7d2f1"}, {"modality": "lidar", "channel": "LIDAR_FRONT_RIGHT", "token": "953faed96fd3d2fae3ec03cd2838b312b8c1a9bb7a0629481982870cb28acb67"}, {"modality": "camera", "channel": "CAM_BACK", "token": "172a55e2b50f18a6b6d545369a457003c2f3b438d0180b2b4c7819ca29b3f6ab"}, {"modality": "camera", "channel": "CAM_BACK_RIGHT", "token": "8e0259a868ddbfe589c2ce9c8bfb34a9e6c19c108b882c45433c76b70a2491a2"}, {"modality": "camera", "channel": "CAM_FRONT_ZOOMED", "token": "286718e1fbc8c8f0ca441969d91c36a8a809666e049e54ce121636100b520946"}, {"modality": "camera", "channel": "CAM_FRONT_RIGHT", "token": "de29f3ebb9d96988ac2c5913022c3102a51134e950284aac2e8511f83aff9a81"}] 2 | -------------------------------------------------------------------------------- /tests/data/lyft/v1.01-train/v1.01-train/visibility.json: -------------------------------------------------------------------------------- 1 | [{"level": "v60-80", "description": "visibility of whole object is between 60 and 80%", "token": "3"}, {"level": "v0-40", "description": "visibility of whole object is between 0 and 40%", "token": "1"}, {"level": "v40-60", "description": "visibility of whole object is between 40 and 60%", "token": "2"}, {"level": "v80-100", "description": "visibility of whole object is between 80 and 100%", "token": "4"}] 2 | -------------------------------------------------------------------------------- /tests/data/lyft/val.txt: -------------------------------------------------------------------------------- 1 | host-a101-lidar0-1240710366399037786-1240710391298976894 2 | -------------------------------------------------------------------------------- /tests/data/nuscenes/mono3d_sample_results.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/nuscenes/mono3d_sample_results.pkl -------------------------------------------------------------------------------- /tests/data/nuscenes/nus_info.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/nuscenes/nus_info.pkl -------------------------------------------------------------------------------- /tests/data/nuscenes/samples/CAM_BACK_LEFT/n015-2018-07-18-11-07-57+0800__CAM_BACK_LEFT__1531883530447423.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/nuscenes/samples/CAM_BACK_LEFT/n015-2018-07-18-11-07-57+0800__CAM_BACK_LEFT__1531883530447423.jpg -------------------------------------------------------------------------------- /tests/data/nuscenes/samples/LIDAR_TOP/n015-2018-08-02-17-16-37+0800__LIDAR_TOP__1533201470948018.pcd.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/nuscenes/samples/LIDAR_TOP/n015-2018-08-02-17-16-37+0800__LIDAR_TOP__1533201470948018.pcd.bin -------------------------------------------------------------------------------- /tests/data/nuscenes/sweeps/LIDAR_TOP/n008-2018-09-18-12-07-26-0400__LIDAR_TOP__1537287083900561.pcd.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/nuscenes/sweeps/LIDAR_TOP/n008-2018-09-18-12-07-26-0400__LIDAR_TOP__1537287083900561.pcd.bin -------------------------------------------------------------------------------- /tests/data/nuscenes/sweeps/LIDAR_TOP/n015-2018-08-02-17-16-37+0800__LIDAR_TOP__1533201470898274.pcd.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/nuscenes/sweeps/LIDAR_TOP/n015-2018-08-02-17-16-37+0800__LIDAR_TOP__1533201470898274.pcd.bin -------------------------------------------------------------------------------- /tests/data/ops/features_for_fps_distance.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/ops/features_for_fps_distance.npy -------------------------------------------------------------------------------- /tests/data/ops/fps_idx.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/ops/fps_idx.npy -------------------------------------------------------------------------------- /tests/data/s3dis/instance_mask/Area_1_office_2.bin: -------------------------------------------------------------------------------- 1 |   2 |  3 |   4 |      -------------------------------------------------------------------------------- /tests/data/s3dis/points/Area_1_office_2.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/s3dis/points/Area_1_office_2.bin -------------------------------------------------------------------------------- /tests/data/s3dis/s3dis_infos.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/s3dis/s3dis_infos.pkl -------------------------------------------------------------------------------- /tests/data/s3dis/semantic_mask/Area_1_office_2.bin: -------------------------------------------------------------------------------- 1 |   2 |     3 |  4 |    -------------------------------------------------------------------------------- /tests/data/scannet/instance_mask/scene0000_00.bin: -------------------------------------------------------------------------------- 1 | 8 2 | #+ 3 | (!8  4 | ,5 %!! 5 | @9. 6 | % 7 | 8 | 9 |  8&89" 10 | 0 11 | 7 ! !9&!  12 | 9!& 13 | ( 14 | -------------------------------------------------------------------------------- /tests/data/scannet/points/scene0000_00.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/scannet/points/scene0000_00.bin -------------------------------------------------------------------------------- /tests/data/scannet/scannet_infos.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/scannet/scannet_infos.pkl -------------------------------------------------------------------------------- /tests/data/scannet/semantic_mask/scene0000_00.bin: -------------------------------------------------------------------------------- 1 | &(&!&((!((& -------------------------------------------------------------------------------- /tests/data/semantickitti/semantickitti_infos.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/semantickitti/semantickitti_infos.pkl -------------------------------------------------------------------------------- /tests/data/semantickitti/sequences/00/labels/000000.label: -------------------------------------------------------------------------------- 1 | 222FF22F22FG4F222222222F2G2FFP2FFFGF22F2PF2F2FF2 -------------------------------------------------------------------------------- /tests/data/semantickitti/sequences/00/velodyne/000000.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/semantickitti/sequences/00/velodyne/000000.bin -------------------------------------------------------------------------------- /tests/data/sunrgbd/points/000001.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/sunrgbd/points/000001.bin -------------------------------------------------------------------------------- /tests/data/sunrgbd/sunrgbd_infos.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/sunrgbd/sunrgbd_infos.pkl -------------------------------------------------------------------------------- /tests/data/sunrgbd/sunrgbd_trainval/image/000001.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/sunrgbd/sunrgbd_trainval/image/000001.jpg -------------------------------------------------------------------------------- /tests/data/waymo/kitti_format/training/image_0/0000000.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/waymo/kitti_format/training/image_0/0000000.png -------------------------------------------------------------------------------- /tests/data/waymo/kitti_format/training/image_0/1000000.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/waymo/kitti_format/training/image_0/1000000.png -------------------------------------------------------------------------------- /tests/data/waymo/kitti_format/training/velodyne/0000000.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/waymo/kitti_format/training/velodyne/0000000.bin -------------------------------------------------------------------------------- /tests/data/waymo/kitti_format/training/velodyne/1000000.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/waymo/kitti_format/training/velodyne/1000000.bin -------------------------------------------------------------------------------- /tests/data/waymo/kitti_format/waymo_dbinfos_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/waymo/kitti_format/waymo_dbinfos_train.pkl -------------------------------------------------------------------------------- /tests/data/waymo/kitti_format/waymo_gt_database/0_Car_0.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/waymo/kitti_format/waymo_gt_database/0_Car_0.bin -------------------------------------------------------------------------------- /tests/data/waymo/kitti_format/waymo_infos_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/waymo/kitti_format/waymo_infos_train.pkl -------------------------------------------------------------------------------- /tests/data/waymo/kitti_format/waymo_infos_val.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/waymo/kitti_format/waymo_infos_val.pkl -------------------------------------------------------------------------------- /tests/data/waymo/waymo_format/gt.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/waymo/waymo_format/gt.bin -------------------------------------------------------------------------------- /tests/data/waymo/waymo_format/validation/val.tfrecord: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/data/waymo/waymo_format/validation/val.tfrecord -------------------------------------------------------------------------------- /tests/test_evaluation/test_functional/test_seg_eval.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import numpy as np 3 | import pytest 4 | import torch 5 | 6 | from mmdet3d.evaluation.functional.seg_eval import seg_eval 7 | 8 | 9 | def test_indoor_eval(): 10 | if not torch.cuda.is_available(): 11 | pytest.skip() 12 | seg_preds = [ 13 | np.array([ 14 | 0, 0, 1, 0, 0, 2, 1, 3, 1, 2, 1, 0, 2, 2, 2, 2, 1, 3, 0, 3, 3, 4, 0 15 | ]) 16 | ] 17 | gt_labels = [ 18 | np.array([ 19 | 0, 0, 0, 4, 0, 0, 1, 1, 1, 4, 1, 1, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 4 20 | ]) 21 | ] 22 | 23 | label2cat = { 24 | 0: 'car', 25 | 1: 'bicycle', 26 | 2: 'motorcycle', 27 | 3: 'truck', 28 | 4: 'unlabeled' 29 | } 30 | ret_value = seg_eval(gt_labels, seg_preds, label2cat, ignore_index=4) 31 | 32 | assert np.isclose(ret_value['car'], 0.428571429) 33 | assert np.isclose(ret_value['bicycle'], 0.428571429) 34 | assert np.isclose(ret_value['motorcycle'], 0.6666667) 35 | assert np.isclose(ret_value['truck'], 0.5) 36 | 37 | assert np.isclose(ret_value['acc'], 0.65) 38 | assert np.isclose(ret_value['acc_cls'], 0.65) 39 | assert np.isclose(ret_value['miou'], 0.50595238) 40 | -------------------------------------------------------------------------------- /tests/test_models/test_backbones/test_cylinder3d_backbone.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import pytest 3 | import torch 4 | 5 | from mmdet3d.registry import MODELS 6 | 7 | 8 | def test_cylinder3d(): 9 | if not torch.cuda.is_available(): 10 | pytest.skip() 11 | cfg = dict( 12 | type='Asymm3DSpconv', 13 | grid_size=[48, 32, 4], 14 | input_channels=16, 15 | base_channels=32, 16 | norm_cfg=dict(type='BN1d', eps=1e-5, momentum=0.1)) 17 | self = MODELS.build(cfg) 18 | self.cuda() 19 | 20 | batch_size = 1 21 | coorx = torch.randint(0, 48, (50, 1)) 22 | coory = torch.randint(0, 36, (50, 1)) 23 | coorz = torch.randint(0, 4, (50, 1)) 24 | coorbatch = torch.zeros(50, 1) 25 | coors = torch.cat([coorbatch, coorx, coory, coorz], dim=1).cuda() 26 | voxel_features = torch.rand(50, 16).cuda() 27 | 28 | # test forward 29 | feature = self(voxel_features, coors, batch_size) 30 | 31 | assert feature.features.shape == (50, 128) 32 | assert feature.indices.data.shape == (50, 4) 33 | -------------------------------------------------------------------------------- /tests/test_models/test_backbones/test_dla.py: -------------------------------------------------------------------------------- 1 | import torch 2 | 3 | from mmdet3d.registry import MODELS 4 | 5 | 6 | def test_dla_net(): 7 | # test DLANet used in SMOKE 8 | # test list config 9 | cfg = dict( 10 | type='DLANet', 11 | depth=34, 12 | in_channels=3, 13 | norm_cfg=dict(type='GN', num_groups=32)) 14 | 15 | img = torch.randn((4, 3, 32, 32)) 16 | self = MODELS.build(cfg) 17 | self.init_weights() 18 | 19 | results = self(img) 20 | assert len(results) == 6 21 | assert results[0].shape == torch.Size([4, 16, 32, 32]) 22 | assert results[1].shape == torch.Size([4, 32, 16, 16]) 23 | assert results[2].shape == torch.Size([4, 64, 8, 8]) 24 | assert results[3].shape == torch.Size([4, 128, 4, 4]) 25 | assert results[4].shape == torch.Size([4, 256, 2, 2]) 26 | assert results[5].shape == torch.Size([4, 512, 1, 1]) 27 | -------------------------------------------------------------------------------- /tests/test_models/test_backbones/test_minkunet_backbone.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import pytest 3 | import torch 4 | import torch.nn.functional as F 5 | 6 | from mmdet3d.registry import MODELS 7 | 8 | 9 | def test_minkunet_backbone(): 10 | if not torch.cuda.is_available(): 11 | pytest.skip('test requires GPU and torch+cuda') 12 | 13 | try: 14 | import torchsparse # noqa: F401 15 | except ImportError: 16 | pytest.skip('test requires Torchsparse installation') 17 | 18 | coordinates, features = [], [] 19 | for i in range(2): 20 | c = torch.randint(0, 16, (100, 3)).int() 21 | c = F.pad(c, (0, 1), mode='constant', value=i) 22 | coordinates.append(c) 23 | f = torch.rand(100, 4) 24 | features.append(f) 25 | features = torch.cat(features, dim=0).cuda() 26 | coordinates = torch.cat(coordinates, dim=0).cuda() 27 | 28 | cfg = dict(type='MinkUNetBackbone') 29 | self = MODELS.build(cfg).cuda() 30 | self.init_weights() 31 | 32 | y = self(features, coordinates) 33 | assert y.shape == torch.Size([200, 96]) 34 | -------------------------------------------------------------------------------- /tests/test_models/test_backbones/test_spvcnn_backbone.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import pytest 3 | import torch 4 | import torch.nn.functional as F 5 | 6 | from mmdet3d.registry import MODELS 7 | 8 | 9 | def test_spvcnn_backbone(): 10 | if not torch.cuda.is_available(): 11 | pytest.skip('test requires GPU and torch+cuda') 12 | 13 | try: 14 | import torchsparse # noqa: F401 15 | except ImportError: 16 | pytest.skip('test requires Torchsparse installation') 17 | 18 | coordinates, features = [], [] 19 | for i in range(2): 20 | c = torch.randint(0, 10, (100, 3)).int() 21 | c = F.pad(c, (0, 1), mode='constant', value=i) 22 | coordinates.append(c) 23 | f = torch.rand(100, 4) 24 | features.append(f) 25 | features = torch.cat(features, dim=0).cuda() 26 | coordinates = torch.cat(coordinates, dim=0).cuda() 27 | 28 | cfg = dict(type='SPVCNNBackbone') 29 | self = MODELS.build(cfg).cuda() 30 | self.init_weights() 31 | 32 | y = self(features, coordinates) 33 | assert y.F.shape == torch.Size([200, 96]) 34 | assert y.C.shape == torch.Size([200, 4]) 35 | -------------------------------------------------------------------------------- /tests/test_models/test_layers/test_dgcnn_modules/test_dgcnn_fa_module.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import pytest 3 | import torch 4 | 5 | 6 | def test_dgcnn_fa_module(): 7 | if not torch.cuda.is_available(): 8 | pytest.skip() 9 | from mmdet3d.models.layers import DGCNNFAModule 10 | 11 | self = DGCNNFAModule(mlp_channels=[24, 16]).cuda() 12 | assert self.mlps.layer0.conv.in_channels == 24 13 | assert self.mlps.layer0.conv.out_channels == 16 14 | 15 | points = [torch.rand(1, 200, 12).float().cuda() for _ in range(3)] 16 | 17 | fa_points = self(points) 18 | assert fa_points.shape == torch.Size([1, 200, 40]) 19 | -------------------------------------------------------------------------------- /tests/test_models/test_layers/test_dgcnn_modules/test_dgcnn_fp_module.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import numpy as np 3 | import pytest 4 | import torch 5 | 6 | 7 | def test_dgcnn_fp_module(): 8 | if not torch.cuda.is_available(): 9 | pytest.skip() 10 | from mmdet3d.models.layers import DGCNNFPModule 11 | 12 | self = DGCNNFPModule(mlp_channels=[24, 16]).cuda() 13 | assert self.mlps.layer0.conv.in_channels == 24 14 | assert self.mlps.layer0.conv.out_channels == 16 15 | 16 | xyz = np.fromfile('tests/data/sunrgbd/points/000001.bin', 17 | np.float32).reshape((-1, 6)) 18 | 19 | # (B, N, 3) 20 | xyz = torch.from_numpy(xyz).view(1, -1, 3).cuda() 21 | points = xyz.repeat([1, 1, 8]).cuda() 22 | 23 | fp_points = self(points) 24 | assert fp_points.shape == torch.Size([1, 200, 16]) 25 | -------------------------------------------------------------------------------- /tests/test_models/test_layers/test_pointnet_modules/test_point_fp_module.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import numpy as np 3 | import pytest 4 | import torch 5 | 6 | 7 | def test_pointnet_fp_module(): 8 | if not torch.cuda.is_available(): 9 | pytest.skip() 10 | from mmdet3d.models.layers import PointFPModule 11 | 12 | self = PointFPModule(mlp_channels=[24, 16]).cuda() 13 | assert self.mlps.layer0.conv.in_channels == 24 14 | assert self.mlps.layer0.conv.out_channels == 16 15 | 16 | xyz = np.fromfile('tests/data/sunrgbd/points/000001.bin', 17 | np.float32).reshape((-1, 6)) 18 | 19 | # (B, N, 3) 20 | xyz1 = torch.from_numpy(xyz[0::2, :3]).view(1, -1, 3).cuda() 21 | # (B, C1, N) 22 | features1 = xyz1.repeat([1, 1, 4]).transpose(1, 2).contiguous().cuda() 23 | 24 | # (B, M, 3) 25 | xyz2 = torch.from_numpy(xyz[1::3, :3]).view(1, -1, 3).cuda() 26 | # (B, C2, N) 27 | features2 = xyz2.repeat([1, 1, 4]).transpose(1, 2).contiguous().cuda() 28 | 29 | fp_features = self(xyz1, xyz2, features1, features2) 30 | assert fp_features.shape == torch.Size([1, 16, 50]) 31 | -------------------------------------------------------------------------------- /tests/test_models/test_losses/test_multibin_loss.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import pytest 3 | import torch 4 | 5 | from mmdet3d.registry import MODELS 6 | 7 | 8 | def test_multibin_loss(): 9 | from mmdet3d.models.losses import MultiBinLoss 10 | 11 | # reduction should be in ['none', 'mean', 'sum'] 12 | with pytest.raises(AssertionError): 13 | multibin_loss = MultiBinLoss(reduction='l2') 14 | 15 | pred = torch.tensor([[ 16 | 0.81, 0.32, 0.78, 0.52, 0.24, 0.12, 0.32, 0.11, 1.20, 1.30, 0.20, 0.11, 17 | 0.12, 0.11, 0.23, 0.31 18 | ], 19 | [ 20 | 0.02, 0.19, 0.78, 0.22, 0.31, 0.12, 0.22, 0.11, 21 | 1.20, 1.30, 0.45, 0.51, 0.12, 0.11, 0.13, 0.61 22 | ]]) 23 | target = torch.tensor([[1, 1, 0, 0, 2.14, 3.12, 0.68, -2.15], 24 | [1, 1, 0, 0, 3.12, 3.12, 2.34, 1.23]]) 25 | multibin_loss_cfg = dict( 26 | type='MultiBinLoss', reduction='none', loss_weight=1.0) 27 | multibin_loss = MODELS.build(multibin_loss_cfg) 28 | output_multibin_loss = multibin_loss(pred, target, num_dir_bins=4) 29 | expected_multibin_loss = torch.tensor(2.1120) 30 | assert torch.allclose( 31 | output_multibin_loss, expected_multibin_loss, atol=1e-4) 32 | -------------------------------------------------------------------------------- /tests/test_models/test_losses/test_rotated_iou_loss.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | 3 | import numpy as np 4 | import torch 5 | 6 | from mmdet3d.models.losses import RotatedIoU3DLoss 7 | 8 | 9 | def test_rotated_iou_3d_loss(): 10 | 11 | if not torch.cuda.is_available(): 12 | return 13 | 14 | boxes1 = torch.tensor([[.5, .5, .5, 1., 1., 1., .0], 15 | [.5, .5, .5, 1., 1., 1., .0], 16 | [.5, .5, .5, 1., 1., 1., .0], 17 | [.5, .5, .5, 1., 1., 1., .0], 18 | [.5, .5, .5, 1., 1., 1., .0]]).cuda() 19 | boxes2 = torch.tensor([[.5, .5, .5, 1., 1., 1., .0], 20 | [.5, .5, .5, 1., 1., 2., np.pi / 2], 21 | [.5, .5, .5, 1., 1., 1., np.pi / 4], 22 | [1., 1., 1., 1., 1., 1., .0], 23 | [-1.5, -1.5, -1.5, 2.5, 2.5, 2.5, .0]]).cuda() 24 | 25 | expect_ious = 1 - torch.tensor([[1., .5, .7071, 1 / 15, .0]]).cuda() 26 | ious = RotatedIoU3DLoss(reduction='none')(boxes1, boxes2) 27 | assert torch.allclose(ious, expect_ious, atol=1e-4) 28 | -------------------------------------------------------------------------------- /tests/test_models/test_necks/test_imvoxel_neck.py: -------------------------------------------------------------------------------- 1 | import pytest 2 | import torch 3 | 4 | from mmdet3d.registry import MODELS 5 | 6 | 7 | def test_imvoxel_neck(): 8 | if not torch.cuda.is_available(): 9 | pytest.skip('test requires GPU and torch+cuda') 10 | 11 | neck_cfg = dict( 12 | type='OutdoorImVoxelNeck', in_channels=64, out_channels=256) 13 | neck = MODELS.build(neck_cfg).cuda() 14 | inputs = torch.rand([1, 64, 216, 248, 12], device='cuda') 15 | outputs = neck(inputs) 16 | assert outputs[0].shape == (1, 256, 248, 216) 17 | -------------------------------------------------------------------------------- /tests/test_models/test_necks/test_pointnet2_fp_neck.py: -------------------------------------------------------------------------------- 1 | import pytest 2 | import torch 3 | 4 | from mmdet3d.registry import MODELS 5 | 6 | 7 | def test_pointnet2_fp_neck(): 8 | if not torch.cuda.is_available(): 9 | pytest.skip() 10 | 11 | xyzs = [16384, 4096, 1024, 256, 64] 12 | feat_channels = [1, 96, 256, 512, 1024] 13 | channel_num = 5 14 | 15 | sa_xyz = [torch.rand(3, xyzs[i], 3) for i in range(channel_num)] 16 | sa_features = [ 17 | torch.rand(3, feat_channels[i], xyzs[i]) for i in range(channel_num) 18 | ] 19 | 20 | neck_cfg = dict( 21 | type='PointNetFPNeck', 22 | fp_channels=((1536, 512, 512), (768, 512, 512), (608, 256, 256), 23 | (257, 128, 128))) 24 | 25 | neck = MODELS.build(neck_cfg) 26 | neck.init_weights() 27 | 28 | if torch.cuda.is_available(): 29 | sa_xyz = [x.cuda() for x in sa_xyz] 30 | sa_features = [x.cuda() for x in sa_features] 31 | neck.cuda() 32 | 33 | feats_sa = {'sa_xyz': sa_xyz, 'sa_features': sa_features} 34 | outputs = neck(feats_sa) 35 | assert outputs['fp_xyz'].cpu().numpy().shape == (3, 16384, 3) 36 | assert outputs['fp_features'].detach().cpu().numpy().shape == (3, 128, 37 | 16384) 38 | -------------------------------------------------------------------------------- /tests/test_models/test_task_modules/test_coders/test_centerpoint_bbox_coder.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import torch 3 | 4 | from mmdet3d.registry import TASK_UTILS 5 | 6 | 7 | def test_centerpoint_bbox_coder(): 8 | bbox_coder_cfg = dict( 9 | type='CenterPointBBoxCoder', 10 | post_center_range=[-61.2, -61.2, -10.0, 61.2, 61.2, 10.0], 11 | max_num=500, 12 | score_threshold=0.1, 13 | pc_range=[-51.2, -51.2], 14 | out_size_factor=4, 15 | voxel_size=[0.2, 0.2]) 16 | 17 | bbox_coder = TASK_UTILS.build(bbox_coder_cfg) 18 | 19 | batch_dim = torch.rand([2, 3, 128, 128]) 20 | batch_hei = torch.rand([2, 1, 128, 128]) 21 | batch_hm = torch.rand([2, 2, 128, 128]) 22 | batch_reg = torch.rand([2, 2, 128, 128]) 23 | batch_rotc = torch.rand([2, 1, 128, 128]) 24 | batch_rots = torch.rand([2, 1, 128, 128]) 25 | batch_vel = torch.rand([2, 2, 128, 128]) 26 | 27 | temp = bbox_coder.decode(batch_hm, batch_rots, batch_rotc, batch_hei, 28 | batch_dim, batch_vel, batch_reg, 5) 29 | for i in range(len(temp)): 30 | assert temp[i]['bboxes'].shape == torch.Size([500, 9]) 31 | assert temp[i]['scores'].shape == torch.Size([500]) 32 | assert temp[i]['labels'].shape == torch.Size([500]) 33 | -------------------------------------------------------------------------------- /tests/test_models/test_task_modules/test_voxel/test_voxel_generator.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import numpy as np 3 | 4 | from mmdet3d.models.task_modules.voxel import VoxelGenerator 5 | 6 | 7 | def test_voxel_generator(): 8 | np.random.seed(0) 9 | voxel_size = [5, 5, 1] 10 | point_cloud_range = [0, 0, 0, 20, 40, 4] 11 | max_num_points = 5 12 | self = VoxelGenerator(voxel_size, point_cloud_range, max_num_points) 13 | points = np.random.uniform(0, 4, (20, 3)) 14 | voxels = self.generate(points) 15 | voxels, coors, num_points_per_voxel = voxels 16 | expected_coors = np.array([[2, 0, 0], [3, 0, 0], [0, 0, 0], [1, 0, 0]]) 17 | expected_num_points_per_voxel = np.array([5, 5, 5, 3]) 18 | assert voxels.shape == (4, 5, 3) 19 | assert np.all(coors == expected_coors) 20 | assert np.all(num_points_per_voxel == expected_num_points_per_voxel) 21 | -------------------------------------------------------------------------------- /tests/test_models/test_voxel_encoders/test_pillar_encoder.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import pytest 3 | import torch 4 | 5 | from mmdet3d.registry import MODELS 6 | 7 | 8 | def test_pillar_feature_net(): 9 | if not torch.cuda.is_available(): 10 | pytest.skip('test requires GPU and torch+cuda') 11 | pillar_feature_net_cfg = dict( 12 | type='PillarFeatureNet', 13 | in_channels=5, 14 | feat_channels=[64], 15 | with_distance=False, 16 | voxel_size=(0.2, 0.2, 8), 17 | point_cloud_range=(-51.2, -51.2, -5.0, 51.2, 51.2, 3.0), 18 | norm_cfg=dict(type='BN1d', eps=1e-3, momentum=0.01)) 19 | pillar_feature_net = MODELS.build(pillar_feature_net_cfg) 20 | 21 | features = torch.rand([97297, 20, 5]) 22 | num_voxels = torch.randint(1, 100, [97297]) 23 | coors = torch.randint(0, 100, [97297, 4]) 24 | 25 | features = pillar_feature_net(features, num_voxels, coors) 26 | assert features.shape == torch.Size([97297, 64]) 27 | -------------------------------------------------------------------------------- /tests/test_samples/parta2_roihead_inputs.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-mmlab/mmdetection3d/fe25f7a51d36e3702f961e198894580d83c4387b/tests/test_samples/parta2_roihead_inputs.npz -------------------------------------------------------------------------------- /tools/create_data.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | set -x 4 | export PYTHONPATH=`pwd`:$PYTHONPATH 5 | 6 | PARTITION=$1 7 | JOB_NAME=$2 8 | DATASET=$3 9 | WORKERS=$4 10 | GPUS=${GPUS:-1} 11 | GPUS_PER_NODE=${GPUS_PER_NODE:-1} 12 | SRUN_ARGS=${SRUN_ARGS:-""} 13 | PY_ARGS=${@:5} 14 | 15 | srun -p ${PARTITION} \ 16 | --job-name=${JOB_NAME} \ 17 | --gres=gpu:${GPUS_PER_NODE} \ 18 | --ntasks=${GPUS} \ 19 | --ntasks-per-node=${GPUS_PER_NODE} \ 20 | --kill-on-bad-exit=1 \ 21 | ${SRUN_ARGS} \ 22 | python -u tools/create_data.py ${DATASET} \ 23 | --root-path ./data/${DATASET} \ 24 | --out-dir ./data/${DATASET} \ 25 | --workers ${WORKERS} \ 26 | --extra-tag ${DATASET} \ 27 | ${PY_ARGS} 28 | -------------------------------------------------------------------------------- /tools/dataset_converters/kitti_unzip.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | DOWNLOAD_DIR=$1 # The directory where the downloaded data set is stored 4 | DATA_ROOT=$2 # The root directory of the converted dataset 5 | 6 | for zip_file in $DOWNLOAD_DIR/KITTI_Object/raw/*.zip; do 7 | echo "Unzipping $zip_file to $DATA_ROOT ......" 8 | unzip -oq $zip_file -d $DATA_ROOT 9 | echo "[Done] Unzip $zip_file to $DATA_ROOT" 10 | # delete the original files 11 | rm -f $zip_file 12 | done 13 | -------------------------------------------------------------------------------- /tools/dataset_converters/nuscenes_unzip.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | DOWNLOAD_DIR=$1 # The directory where the downloaded data set is stored 4 | DATA_ROOT=$2 # The root directory of the converted dataset 5 | 6 | for split in $DOWNLOAD_DIR/nuScenes/raw/*; do 7 | for tgz_file in $split/*; do 8 | if [[ $tgz_file == *.tgz ]] 9 | then 10 | echo "Unzipping $tgz_file to $DATA_ROOT ......" 11 | tar -zxvf $tgz_file -C $DATA_ROOT/ 12 | echo "[Done] Unzip $tgz_file to $DATA_ROOT" 13 | fi 14 | # delete the original files 15 | rm -f $tgz_file 16 | done 17 | done 18 | -------------------------------------------------------------------------------- /tools/dataset_converters/semantickitti_unzip.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | DOWNLOAD_DIR=$1 # The directory where the downloaded data set is stored 4 | DATA_ROOT=$2 # The root directory of the converted dataset 5 | 6 | for zip_file in $DOWNLOAD_DIR/SemanticKITTI/raw/*.zip; do 7 | echo "Unzipping $zip_file to $DATA_ROOT ......" 8 | unzip -oq $zip_file -d $DATA_ROOT 9 | echo "[Done] Unzip $zip_file to $DATA_ROOT" 10 | # delete the original files 11 | rm -f $zip_file 12 | done 13 | -------------------------------------------------------------------------------- /tools/dist_test.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | CONFIG=$1 4 | CHECKPOINT=$2 5 | GPUS=$3 6 | NNODES=${NNODES:-1} 7 | NODE_RANK=${NODE_RANK:-0} 8 | PORT=${PORT:-29500} 9 | MASTER_ADDR=${MASTER_ADDR:-"127.0.0.1"} 10 | 11 | PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \ 12 | python -m torch.distributed.launch \ 13 | --nnodes=$NNODES \ 14 | --node_rank=$NODE_RANK \ 15 | --master_addr=$MASTER_ADDR \ 16 | --nproc_per_node=$GPUS \ 17 | --master_port=$PORT \ 18 | $(dirname "$0")/test.py \ 19 | $CONFIG \ 20 | $CHECKPOINT \ 21 | --launcher pytorch \ 22 | ${@:4} 23 | -------------------------------------------------------------------------------- /tools/dist_train.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | CONFIG=$1 4 | GPUS=$2 5 | NNODES=${NNODES:-1} 6 | NODE_RANK=${NODE_RANK:-0} 7 | PORT=${PORT:-29500} 8 | MASTER_ADDR=${MASTER_ADDR:-"127.0.0.1"} 9 | 10 | PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \ 11 | python -m torch.distributed.launch \ 12 | --nnodes=$NNODES \ 13 | --node_rank=$NODE_RANK \ 14 | --master_addr=$MASTER_ADDR \ 15 | --nproc_per_node=$GPUS \ 16 | --master_port=$PORT \ 17 | $(dirname "$0")/train.py \ 18 | $CONFIG \ 19 | --launcher pytorch ${@:3} 20 | -------------------------------------------------------------------------------- /tools/misc/print_config.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import argparse 3 | 4 | from mmengine import Config, DictAction 5 | 6 | 7 | def parse_args(): 8 | parser = argparse.ArgumentParser(description='Print the whole config') 9 | parser.add_argument('config', help='config file path') 10 | parser.add_argument( 11 | '--options', nargs='+', action=DictAction, help='arguments in dict') 12 | args = parser.parse_args() 13 | 14 | return args 15 | 16 | 17 | def main(): 18 | args = parse_args() 19 | 20 | cfg = Config.fromfile(args.config) 21 | if args.options is not None: 22 | cfg.merge_from_dict(args.options) 23 | print(f'Config:\n{cfg.pretty_text}') 24 | 25 | 26 | if __name__ == '__main__': 27 | main() 28 | -------------------------------------------------------------------------------- /tools/model_converters/publish_model.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) OpenMMLab. All rights reserved. 2 | import argparse 3 | import subprocess 4 | 5 | import torch 6 | 7 | 8 | def parse_args(): 9 | parser = argparse.ArgumentParser( 10 | description='Process a checkpoint to be published') 11 | parser.add_argument('in_file', help='input checkpoint filename') 12 | parser.add_argument('out_file', help='output checkpoint filename') 13 | args = parser.parse_args() 14 | return args 15 | 16 | 17 | def process_checkpoint(in_file, out_file): 18 | checkpoint = torch.load(in_file, map_location='cpu') 19 | # remove optimizer for smaller file size 20 | if 'optimizer' in checkpoint: 21 | del checkpoint['optimizer'] 22 | # if it is necessary to remove some sensitive data in checkpoint['meta'], 23 | # add the code here. 24 | torch.save(checkpoint, out_file) 25 | sha = subprocess.check_output(['sha256sum', out_file]).decode() 26 | final_file = out_file.rstrip('.pth') + '-{}.pth'.format(sha[:8]) 27 | subprocess.Popen(['mv', out_file, final_file]) 28 | 29 | 30 | def main(): 31 | args = parse_args() 32 | process_checkpoint(args.in_file, args.out_file) 33 | 34 | 35 | if __name__ == '__main__': 36 | main() 37 | -------------------------------------------------------------------------------- /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" ${PY_ARGS} 25 | -------------------------------------------------------------------------------- /tools/update_data_coords.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | set -x 4 | export PYTHONPATH=`pwd`:$PYTHONPATH 5 | 6 | PARTITION=$1 7 | DATASET=$2 8 | GPUS=${GPUS:-1} 9 | GPUS_PER_NODE=${GPUS_PER_NODE:-1} 10 | SRUN_ARGS=${SRUN_ARGS:-""} 11 | JOB_NAME=update_data_coords 12 | 13 | srun -p ${PARTITION} \ 14 | --job-name=${JOB_NAME} \ 15 | --gres=gpu:${GPUS_PER_NODE} \ 16 | --ntasks=${GPUS} \ 17 | --ntasks-per-node=${GPUS_PER_NODE} \ 18 | --kill-on-bad-exit=1 \ 19 | ${SRUN_ARGS} \ 20 | python -u tools/update_data_coords.py ${DATASET} \ 21 | --root-dir ./data/${DATASET} \ 22 | --out-dir ./data/${DATASET} 23 | --------------------------------------------------------------------------------