[Feature] Support new config type (#2608)

* support new configs

* support new configs

* verify configs

mmdet3d/configs/centerpoint/__init__.py

+# Copyright (c) OpenMMLab. All rights reserved.

mmdet3d/configs/centerpoint/centerpoint_pillar02_second_secfpn_8xb4_cyclic_20e_nus_3d.py

+# Copyright (c) OpenMMLab. All rights reserved.
+if '_base_':
+    from .._base_.datasets.nus_3d import *
+    from .._base_.models.centerpoint_pillar02_second_secfpn_nus import *
+    from .._base_.schedules.cyclic_20e import *
+    from .._base_.default_runtime import *
+
+from mmengine.dataset.sampler import DefaultSampler
+
+from mmdet3d.datasets.dataset_wrappers import CBGSDataset
+from mmdet3d.datasets.nuscenes_dataset import NuScenesDataset
+from mmdet3d.datasets.transforms.formating import Pack3DDetInputs
+from mmdet3d.datasets.transforms.loading import (LoadAnnotations3D,
+                                                 LoadPointsFromFile,
+                                                 LoadPointsFromMultiSweeps)
+from mmdet3d.datasets.transforms.test_time_aug import MultiScaleFlipAug3D
+from mmdet3d.datasets.transforms.transforms_3d import (  # noqa
+    GlobalRotScaleTrans, ObjectNameFilter, ObjectRangeFilter, ObjectSample,
+    PointShuffle, PointsRangeFilter, RandomFlip3D)
+
+# If point cloud range is changed, the models should also change their point
+# cloud range accordingly
+point_cloud_range = [-51.2, -51.2, -5.0, 51.2, 51.2, 3.0]
+# Using calibration info convert the Lidar-coordinate point cloud range to the
+# ego-coordinate point cloud range could bring a little promotion in nuScenes.
+# point_cloud_range = [-51.2, -52, -5.0, 51.2, 50.4, 3.0]
+# For nuScenes we usually do 10-class detection
+class_names = [
+    'car', 'truck', 'construction_vehicle', 'bus', 'trailer', 'barrier',
+    'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone'
+]
+data_prefix.merge(
+    dict(pts='samples/LIDAR_TOP', img='', sweeps='sweeps/LIDAR_TOP'))
+model.merge(
+    dict(
+        data_preprocessor=dict(
+            voxel_layer=dict(point_cloud_range=point_cloud_range)),
+        pts_voxel_encoder=dict(point_cloud_range=point_cloud_range),
+        pts_bbox_head=dict(bbox_coder=dict(pc_range=point_cloud_range[:2])),
+        # model training and testing settings
+        train_cfg=dict(pts=dict(point_cloud_range=point_cloud_range)),
+        test_cfg=dict(pts=dict(pc_range=point_cloud_range[:2]))))
+
+dataset_type = 'NuScenesDataset'
+data_root = 'data/nuscenes/'
+backend_args = None
+
+db_sampler = dict(
+    data_root=data_root,
+    info_path=data_root + 'nuscenes_dbinfos_train.pkl',
+    rate=1.0,
+    prepare=dict(
+        filter_by_difficulty=[-1],
+        filter_by_min_points=dict(
+            car=5,
+            truck=5,
+            bus=5,
+            trailer=5,
+            construction_vehicle=5,
+            traffic_cone=5,
+            barrier=5,
+            motorcycle=5,
+            bicycle=5,
+            pedestrian=5)),
+    classes=class_names,
+    sample_groups=dict(
+        car=2,
+        truck=3,
+        construction_vehicle=7,
+        bus=4,
+        trailer=6,
+        barrier=2,
+        motorcycle=6,
+        bicycle=6,
+        pedestrian=2,
+        traffic_cone=2),
+    points_loader=dict(
+        type=LoadPointsFromFile,
+        coord_type='LIDAR',
+        load_dim=5,
+        use_dim=[0, 1, 2, 3, 4],
+        backend_args=backend_args),
+    backend_args=backend_args)
+
+train_pipeline = [
+    dict(
+        type=LoadPointsFromFile,
+        coord_type='LIDAR',
+        load_dim=5,
+        use_dim=5,
+        backend_args=backend_args),
+    dict(
+        type=LoadPointsFromMultiSweeps,
+        sweeps_num=9,
+        use_dim=[0, 1, 2, 3, 4],
+        pad_empty_sweeps=True,
+        remove_close=True,
+        backend_args=backend_args),
+    dict(type=LoadAnnotations3D, with_bbox_3d=True, with_label_3d=True),
+    dict(type=ObjectSample, db_sampler=db_sampler),
+    dict(
+        type=GlobalRotScaleTrans,
+        rot_range=[-0.3925, 0.3925],
+        scale_ratio_range=[0.95, 1.05],
+        translation_std=[0, 0, 0]),
+    dict(
+        type=RandomFlip3D,
+        sync_2d=False,
+        flip_ratio_bev_horizontal=0.5,
+        flip_ratio_bev_vertical=0.5),
+    dict(type=PointsRangeFilter, point_cloud_range=point_cloud_range),
+    dict(type=ObjectRangeFilter, point_cloud_range=point_cloud_range),
+    dict(type=ObjectNameFilter, classes=class_names),
+    dict(type=PointShuffle),
+    dict(
+        type=Pack3DDetInputs, keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
+]
+test_pipeline = [
+    dict(
+        type=LoadPointsFromFile,
+        coord_type='LIDAR',
+        load_dim=5,
+        use_dim=5,
+        backend_args=backend_args),
+    dict(
+        type=LoadPointsFromMultiSweeps,
+        sweeps_num=9,
+        use_dim=[0, 1, 2, 3, 4],
+        pad_empty_sweeps=True,
+        remove_close=True,
+        backend_args=backend_args),
+    dict(
+        type=MultiScaleFlipAug3D,
+        img_scale=(1333, 800),
+        pts_scale_ratio=1,
+        flip=False,
+        transforms=[
+            dict(
+                type=GlobalRotScaleTrans,
+                rot_range=[0, 0],
+                scale_ratio_range=[1., 1.],
+                translation_std=[0, 0, 0]),
+            dict(type=RandomFlip3D)
+        ]),
+    dict(type=Pack3DDetInputs, keys=['points'])
+]
+
+train_dataloader.merge(
+    dict(
+        _delete_=True,
+        batch_size=4,
+        num_workers=4,
+        persistent_workers=True,
+        sampler=dict(type=DefaultSampler, shuffle=True),
+        dataset=dict(
+            type=CBGSDataset,
+            dataset=dict(
+                type=NuScenesDataset,
+                data_root=data_root,
+                ann_file='nuscenes_infos_train.pkl',
+                pipeline=train_pipeline,
+                metainfo=dict(classes=class_names),
+                test_mode=False,
+                data_prefix=data_prefix,
+                use_valid_flag=True,
+                # we use box_type_3d='LiDAR' in kitti and nuscenes dataset
+                # and box_type_3d='Depth' in sunrgbd and scannet dataset.
+                box_type_3d='LiDAR',
+                backend_args=backend_args))))
+test_dataloader.merge(
+    dict(
+        dataset=dict(
+            pipeline=test_pipeline, metainfo=dict(classes=class_names))))
+val_dataloader.merge(
+    dict(
+        dataset=dict(
+            pipeline=test_pipeline, metainfo=dict(classes=class_names))))
+
+train_cfg.merge(dict(val_interval=20))

mmdet3d/configs/centerpoint/centerpoint_voxel01_second_secfpn_8xb4_cyclic_20e_nus_3d.py

+# Copyright (c) OpenMMLab. All rights reserved.
+if '_base_':
+    from .._base_.datasets.nus_3d import *
+    from .._base_.models.centerpoint_voxel01_second_secfpn_nus import *
+    from .._base_.schedules.cyclic_20e import *
+    from .._base_.default_runtime import *
+
+from mmengine.dataset.sampler import DefaultSampler
+
+from mmdet3d.datasets.dataset_wrappers import CBGSDataset
+from mmdet3d.datasets.nuscenes_dataset import NuScenesDataset
+from mmdet3d.datasets.transforms.formating import Pack3DDetInputs
+from mmdet3d.datasets.transforms.loading import (LoadAnnotations3D,
+                                                 LoadPointsFromFile,
+                                                 LoadPointsFromMultiSweeps)
+from mmdet3d.datasets.transforms.test_time_aug import MultiScaleFlipAug3D
+from mmdet3d.datasets.transforms.transforms_3d import (  # noqa
+    GlobalRotScaleTrans, ObjectNameFilter, ObjectRangeFilter, ObjectSample,
+    PointShuffle, PointsRangeFilter, RandomFlip3D)
+
+# If point cloud range is changed, the models should also change their point
+# cloud range accordingly
+point_cloud_range = [-51.2, -51.2, -5.0, 51.2, 51.2, 3.0]
+# Using calibration info convert the Lidar-coordinate point cloud range to the
+# ego-coordinate point cloud range could bring a little promotion in nuScenes.
+# point_cloud_range = [-51.2, -52, -5.0, 51.2, 50.4, 3.0]
+# For nuScenes we usually do 10-class detection
+class_names = [
+    'car', 'truck', 'construction_vehicle', 'bus', 'trailer', 'barrier',
+    'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone'
+]
+data_prefix.merge(
+    dict(pts='samples/LIDAR_TOP', img='', sweeps='sweeps/LIDAR_TOP'))
+model.merge(
+    dict(
+        data_preprocessor=dict(
+            voxel_layer=dict(point_cloud_range=point_cloud_range)),
+        pts_bbox_head=dict(bbox_coder=dict(pc_range=point_cloud_range[:2])),
+        # model training and testing settings
+        train_cfg=dict(pts=dict(point_cloud_range=point_cloud_range)),
+        test_cfg=dict(pts=dict(pc_range=point_cloud_range[:2]))))
+
+dataset_type = 'NuScenesDataset'
+data_root = 'data/nuscenes/'
+backend_args = None
+
+db_sampler = dict(
+    data_root=data_root,
+    info_path=data_root + 'nuscenes_dbinfos_train.pkl',
+    rate=1.0,
+    prepare=dict(
+        filter_by_difficulty=[-1],
+        filter_by_min_points=dict(
+            car=5,
+            truck=5,
+            bus=5,
+            trailer=5,
+            construction_vehicle=5,
+            traffic_cone=5,
+            barrier=5,
+            motorcycle=5,
+            bicycle=5,
+            pedestrian=5)),
+    classes=class_names,
+    sample_groups=dict(
+        car=2,
+        truck=3,
+        construction_vehicle=7,
+        bus=4,
+        trailer=6,
+        barrier=2,
+        motorcycle=6,
+        bicycle=6,
+        pedestrian=2,
+        traffic_cone=2),
+    points_loader=dict(
+        type=LoadPointsFromFile,
+        coord_type='LIDAR',
+        load_dim=5,
+        use_dim=[0, 1, 2, 3, 4],
+        backend_args=backend_args),
+    backend_args=backend_args)
+
+train_pipeline = [
+    dict(
+        type=LoadPointsFromFile,
+        coord_type='LIDAR',
+        load_dim=5,
+        use_dim=5,
+        backend_args=backend_args),
+    dict(
+        type=LoadPointsFromMultiSweeps,
+        sweeps_num=9,
+        use_dim=[0, 1, 2, 3, 4],
+        pad_empty_sweeps=True,
+        remove_close=True,
+        backend_args=backend_args),
+    dict(type=LoadAnnotations3D, with_bbox_3d=True, with_label_3d=True),
+    dict(type=ObjectSample, db_sampler=db_sampler),
+    dict(
+        type=GlobalRotScaleTrans,
+        rot_range=[-0.3925, 0.3925],
+        scale_ratio_range=[0.95, 1.05],
+        translation_std=[0, 0, 0]),
+    dict(
+        type=RandomFlip3D,
+        sync_2d=False,
+        flip_ratio_bev_horizontal=0.5,
+        flip_ratio_bev_vertical=0.5),
+    dict(type=PointsRangeFilter, point_cloud_range=point_cloud_range),
+    dict(type=ObjectRangeFilter, point_cloud_range=point_cloud_range),
+    dict(type=ObjectNameFilter, classes=class_names),
+    dict(type=PointShuffle),
+    dict(
+        type=Pack3DDetInputs, keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
+]
+test_pipeline = [
+    dict(
+        type=LoadPointsFromFile,
+        coord_type='LIDAR',
+        load_dim=5,
+        use_dim=5,
+        backend_args=backend_args),
+    dict(
+        type=LoadPointsFromMultiSweeps,
+        sweeps_num=9,
+        use_dim=[0, 1, 2, 3, 4],
+        pad_empty_sweeps=True,
+        remove_close=True,
+        backend_args=backend_args),
+    dict(
+        type=MultiScaleFlipAug3D,
+        img_scale=(1333, 800),
+        pts_scale_ratio=1,
+        flip=False,
+        transforms=[
+            dict(
+                type=GlobalRotScaleTrans,
+                rot_range=[0, 0],
+                scale_ratio_range=[1., 1.],
+                translation_std=[0, 0, 0]),
+            dict(type=RandomFlip3D),
+            dict(type=PointsRangeFilter, point_cloud_range=point_cloud_range)
+        ]),
+    dict(type=Pack3DDetInputs, keys=['points'])
+]
+
+train_dataloader.merge(
+    dict(
+        _delete_=True,
+        batch_size=4,
+        num_workers=4,
+        persistent_workers=True,
+        sampler=dict(type=DefaultSampler, shuffle=True),
+        dataset=dict(
+            type=CBGSDataset,
+            dataset=dict(
+                type=NuScenesDataset,
+                data_root=data_root,
+                ann_file='nuscenes_infos_train.pkl',
+                pipeline=train_pipeline,
+                metainfo=dict(classes=class_names),
+                test_mode=False,
+                data_prefix=data_prefix,
+                use_valid_flag=True,
+                # we use box_type_3d='LiDAR' in kitti and nuscenes dataset
+                # and box_type_3d='Depth' in sunrgbd and scannet dataset.
+                box_type_3d='LiDAR',
+                backend_args=backend_args))))
+test_dataloader.merge(
+    dict(
+        dataset=dict(
+            pipeline=test_pipeline, metainfo=dict(classes=class_names))))
+val_dataloader.merge(
+    dict(
+        dataset=dict(
+            pipeline=test_pipeline, metainfo=dict(classes=class_names))))
+
+train_cfg.merge(dict(val_interval=20))

mmdet3d/configs/minkunet/__init__.py

+# Copyright (c) OpenMMLab. All rights reserved.

mmdet3d/configs/minkunet/minkunet34_w32_torchsparse_8xb2_laser_polar_mix_3x_semantickitti.py

+# Copyright (c) OpenMMLab. All rights reserved.
+if '_base_':
+    from .._base_.datasets.semantickitti import *
+    from .._base_.models.minkunet import *
+    from .._base_.schedules.schedule_3x import *
+    from .._base_.default_runtime import *
+
+from mmcv.transforms.wrappers import RandomChoice
+from mmengine.hooks.checkpoint_hook import CheckpointHook
+
+from mmdet3d.datasets.transforms.formating import Pack3DDetInputs
+from mmdet3d.datasets.transforms.loading import (LoadAnnotations3D,
+                                                 LoadPointsFromFile,
+                                                 PointSegClassMapping)
+from mmdet3d.datasets.transforms.transforms_3d import (GlobalRotScaleTrans,
+                                                       LaserMix, PolarMix)
+
+model.merge(
+    dict(
+        data_preprocessor=dict(max_voxels=None),
+        backbone=dict(encoder_blocks=[2, 3, 4, 6])))
+
+train_pipeline = [
+    dict(type=LoadPointsFromFile, coord_type='LIDAR', load_dim=4, use_dim=4),
+    dict(
+        type=LoadAnnotations3D,
+        with_bbox_3d=False,
+        with_label_3d=False,
+        with_seg_3d=True,
+        seg_3d_dtype='np.int32',
+        seg_offset=2**16,
+        dataset_type='semantickitti'),
+    dict(type=PointSegClassMapping),
+    dict(
+        type=RandomChoice,
+        transforms=[
+            [
+                dict(
+                    type=LaserMix,
+                    num_areas=[3, 4, 5, 6],
+                    pitch_angles=[-25, 3],
+                    pre_transform=[
+                        dict(
+                            type=LoadPointsFromFile,
+                            coord_type='LIDAR',
+                            load_dim=4,
+                            use_dim=4),
+                        dict(
+                            type=LoadAnnotations3D,
+                            with_bbox_3d=False,
+                            with_label_3d=False,
+                            with_seg_3d=True,
+                            seg_3d_dtype='np.int32',
+                            seg_offset=2**16,
+                            dataset_type='semantickitti'),
+                        dict(type=PointSegClassMapping)
+                    ],
+                    prob=1)
+            ],
+            [
+                dict(
+                    type=PolarMix,
+                    instance_classes=[0, 1, 2, 3, 4, 5, 6, 7],
+                    swap_ratio=0.5,
+                    rotate_paste_ratio=1.0,
+                    pre_transform=[
+                        dict(
+                            type=LoadPointsFromFile,
+                            coord_type='LIDAR',
+                            load_dim=4,
+                            use_dim=4),
+                        dict(
+                            type=LoadAnnotations3D,
+                            with_bbox_3d=False,
+                            with_label_3d=False,
+                            with_seg_3d=True,
+                            seg_3d_dtype='np.int32',
+                            seg_offset=2**16,
+                            dataset_type='semantickitti'),
+                        dict(type=PointSegClassMapping)
+                    ],
+                    prob=1)
+            ],
+        ],
+        prob=[0.5, 0.5]),
+    dict(
+        type=GlobalRotScaleTrans,
+        rot_range=[0., 6.28318531],
+        scale_ratio_range=[0.95, 1.05],
+        translation_std=[0, 0, 0],
+    ),
+    dict(type=Pack3DDetInputs, keys=['points', 'pts_semantic_mask'])
+]
+
+train_dataloader.merge(dict(dataset=dict(pipeline=train_pipeline)))
+
+default_hooks.merge(dict(checkpoint=dict(type=CheckpointHook, interval=1)))

mmdet3d/configs/mvxnet/__init__.py

+# Copyright (c) OpenMMLab. All rights reserved.

mmdet3d/configs/mvxnet/mvxnet_fpn_dv_second_secfpn_8xb2_80e_kitti_3d_3class.py

+# Copyright (c) OpenMMLab. All rights reserved.
+if '_base_':
+    from .._base_.schedules.cosine import *
+    from .._base_.default_runtime import *
+
+from mmcv.transforms.loading import LoadImageFromFile
+from mmcv.transforms.processing import RandomResize, Resize
+from mmengine.dataset.dataset_wrapper import RepeatDataset
+from mmengine.dataset.sampler import DefaultSampler
+from mmengine.visualization.vis_backend import LocalVisBackend
+
+from mmdet3d.datasets.kitti_dataset import KittiDataset
+from mmdet3d.datasets.transforms.formating import Pack3DDetInputs
+from mmdet3d.datasets.transforms.loading import (LoadAnnotations3D,
+                                                 LoadPointsFromFile)
+from mmdet3d.datasets.transforms.test_time_aug import MultiScaleFlipAug3D
+from mmdet3d.datasets.transforms.transforms_3d import (GlobalRotScaleTrans,
+                                                       ObjectRangeFilter,
+                                                       PointShuffle,
+                                                       PointsRangeFilter,
+                                                       RandomFlip3D)
+from mmdet3d.evaluation.metrics.kitti_metric import KittiMetric
+from mmdet3d.models.backbones.second import SECOND
+from mmdet3d.models.data_preprocessors.data_preprocessor import \
+    Det3DDataPreprocessor
+from mmdet3d.models.dense_heads.anchor3d_head import Anchor3DHead
+from mmdet3d.models.detectors.mvx_faster_rcnn import DynamicMVXFasterRCNN
+from mmdet3d.models.layers.fusion_layers.point_fusion import PointFusion
+from mmdet3d.models.middle_encoders.sparse_encoder import SparseEncoder
+from mmdet3d.models.necks.second_fpn import SECONDFPN
+from mmdet3d.models.task_modules.anchor.anchor_3d_generator import \
+    Anchor3DRangeGenerator
+from mmdet3d.models.task_modules.assigners.max_3d_iou_assigner import \
+    Max3DIoUAssigner
+from mmdet3d.models.task_modules.coders.delta_xyzwhlr_bbox_coder import \
+    DeltaXYZWLHRBBoxCoder
+from mmdet3d.models.voxel_encoders.voxel_encoder import DynamicVFE
+from mmdet3d.structures.ops.iou3d_calculator import BboxOverlapsNearest3D
+from mmdet3d.visualization.local_visualizer import Det3DLocalVisualizer
+
+# model settings
+voxel_size = [0.05, 0.05, 0.1]
+point_cloud_range = [0, -40, -3, 70.4, 40, 1]
+
+model = dict(
+    type=DynamicMVXFasterRCNN,
+    data_preprocessor=dict(
+        type=Det3DDataPreprocessor,
+        voxel=True,
+        voxel_type='dynamic',
+        voxel_layer=dict(
+            max_num_points=-1,
+            point_cloud_range=point_cloud_range,
+            voxel_size=voxel_size,
+            max_voxels=(-1, -1)),
+        mean=[102.9801, 115.9465, 122.7717],
+        std=[1.0, 1.0, 1.0],
+        bgr_to_rgb=False,
+        pad_size_divisor=32),
+    img_backbone=dict(
+        type='mmdet.ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=False),
+        norm_eval=True,
+        style='caffe'),
+    img_neck=dict(
+        type='mmdet.FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        # make the image features more stable numerically to avoid loss nan
+        norm_cfg=dict(type='BN', requires_grad=False),
+        num_outs=5),
+    pts_voxel_encoder=dict(
+        type=DynamicVFE,
+        in_channels=4,
+        feat_channels=[64, 64],
+        with_distance=False,
+        voxel_size=voxel_size,
+        with_cluster_center=True,
+        with_voxel_center=True,
+        point_cloud_range=point_cloud_range,
+        fusion_layer=dict(
+            type=PointFusion,
+            img_channels=256,
+            pts_channels=64,
+            mid_channels=128,
+            out_channels=128,
+            img_levels=[0, 1, 2, 3, 4],
+            align_corners=False,
+            activate_out=True,
+            fuse_out=False)),
+    pts_middle_encoder=dict(
+        type=SparseEncoder,
+        in_channels=128,
+        sparse_shape=[41, 1600, 1408],
+        order=('conv', 'norm', 'act')),
+    pts_backbone=dict(
+        type=SECOND,
+        in_channels=256,
+        layer_nums=[5, 5],
+        layer_strides=[1, 2],
+        out_channels=[128, 256]),
+    pts_neck=dict(
+        type=SECONDFPN,
+        in_channels=[128, 256],
+        upsample_strides=[1, 2],
+        out_channels=[256, 256]),
+    pts_bbox_head=dict(
+        type=Anchor3DHead,
+        num_classes=3,
+        in_channels=512,
+        feat_channels=512,
+        use_direction_classifier=True,
+        anchor_generator=dict(
+            type=Anchor3DRangeGenerator,
+            ranges=[
+                [0, -40.0, -0.6, 70.4, 40.0, -0.6],
+                [0, -40.0, -0.6, 70.4, 40.0, -0.6],
+                [0, -40.0, -1.78, 70.4, 40.0, -1.78],
+            ],
+            sizes=[[0.8, 0.6, 1.73], [1.76, 0.6, 1.73], [3.9, 1.6, 1.56]],
+            rotations=[0, 1.57],
+            reshape_out=False),
+        assigner_per_size=True,
+        diff_rad_by_sin=True,
+        assign_per_class=True,
+        bbox_coder=dict(type=DeltaXYZWLHRBBoxCoder),
+        loss_cls=dict(
+            type='mmdet.FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox=dict(
+            type='mmdet.SmoothL1Loss', beta=1.0 / 9.0, loss_weight=2.0),
+        loss_dir=dict(
+            type='mmdet.CrossEntropyLoss', use_sigmoid=False,
+            loss_weight=0.2)),
+    # model training and testing settings
+    train_cfg=dict(
+        pts=dict(
+            assigner=[
+                dict(  # for Pedestrian
+                    type=Max3DIoUAssigner,
+                    iou_calculator=dict(type=BboxOverlapsNearest3D),
+                    pos_iou_thr=0.35,
+                    neg_iou_thr=0.2,
+                    min_pos_iou=0.2,
+                    ignore_iof_thr=-1),
+                dict(  # for Cyclist
+                    type=Max3DIoUAssigner,
+                    iou_calculator=dict(type=BboxOverlapsNearest3D),
+                    pos_iou_thr=0.35,
+                    neg_iou_thr=0.2,
+                    min_pos_iou=0.2,
+                    ignore_iof_thr=-1),
+                dict(  # for Car
+                    type=Max3DIoUAssigner,
+                    iou_calculator=dict(type=BboxOverlapsNearest3D),
+                    pos_iou_thr=0.6,
+                    neg_iou_thr=0.45,
+                    min_pos_iou=0.45,
+                    ignore_iof_thr=-1),
+            ],
+            allowed_border=0,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        pts=dict(
+            use_rotate_nms=True,
+            nms_across_levels=False,
+            nms_thr=0.01,
+            score_thr=0.1,
+            min_bbox_size=0,
+            nms_pre=100,
+            max_num=50)))
+
+# dataset settings
+dataset_type = 'KittiDataset'
+data_root = 'data/kitti/'
+class_names = ['Pedestrian', 'Cyclist', 'Car']
+metainfo = dict(classes=class_names)
+input_modality = dict(use_lidar=True, use_camera=True)
+backend_args = None
+train_pipeline = [
+    dict(
+        type=LoadPointsFromFile,
+        coord_type='LIDAR',
+        load_dim=4,
+        use_dim=4,
+        backend_args=backend_args),
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(type=LoadAnnotations3D, with_bbox_3d=True, with_label_3d=True),
+    dict(type=RandomResize, scale=[(640, 192), (2560, 768)], keep_ratio=True),
+    dict(
+        type=GlobalRotScaleTrans,
+        rot_range=[-0.78539816, 0.78539816],
+        scale_ratio_range=[0.95, 1.05],
+        translation_std=[0.2, 0.2, 0.2]),
+    dict(type=RandomFlip3D, flip_ratio_bev_horizontal=0.5),
+    dict(type=PointsRangeFilter, point_cloud_range=point_cloud_range),
+    dict(type=ObjectRangeFilter, point_cloud_range=point_cloud_range),
+    dict(type=PointShuffle),
+    dict(
+        type=Pack3DDetInputs,
+        keys=[
+            'points', 'img', 'gt_bboxes_3d', 'gt_labels_3d', 'gt_bboxes',
+            'gt_labels'
+        ])
+]
+test_pipeline = [
+    dict(
+        type=LoadPointsFromFile,
+        coord_type='LIDAR',
+        load_dim=4,
+        use_dim=4,
+        backend_args=backend_args),
+    dict(type=LoadImageFromFile, backend_args=backend_args),
+    dict(
+        type=MultiScaleFlipAug3D,
+        img_scale=(1280, 384),
+        pts_scale_ratio=1,
+        flip=False,
+        transforms=[
+            # Temporary solution, fix this after refactor the augtest
+            dict(type=Resize, scale=0, keep_ratio=True),
+            dict(
+                type=GlobalRotScaleTrans,
+                rot_range=[0, 0],
+                scale_ratio_range=[1., 1.],
+                translation_std=[0, 0, 0]),
+            dict(type=RandomFlip3D),
+            dict(type=PointsRangeFilter, point_cloud_range=point_cloud_range),
+        ]),
+    dict(type=Pack3DDetInputs, keys=['points', 'img'])
+]
+modality = dict(use_lidar=True, use_camera=True)
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    sampler=dict(type=DefaultSampler, shuffle=True),
+    dataset=dict(
+        type=RepeatDataset,
+        times=2,
+        dataset=dict(
+            type=KittiDataset,
+            data_root=data_root,
+            modality=modality,
+            ann_file='kitti_infos_train.pkl',
+            data_prefix=dict(
+                pts='training/velodyne_reduced', img='training/image_2'),
+            pipeline=train_pipeline,
+            filter_empty_gt=False,
+            metainfo=metainfo,
+            # we use box_type_3d='LiDAR' in kitti and nuscenes dataset
+            # and box_type_3d='Depth' in sunrgbd and scannet dataset.
+            box_type_3d='LiDAR',
+            backend_args=backend_args)))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=1,
+    sampler=dict(type=DefaultSampler, shuffle=False),
+    dataset=dict(
+        type=KittiDataset,
+        data_root=data_root,
+        modality=modality,
+        ann_file='kitti_infos_val.pkl',
+        data_prefix=dict(
+            pts='training/velodyne_reduced', img='training/image_2'),
+        pipeline=test_pipeline,
+        metainfo=metainfo,
+        test_mode=True,
+        box_type_3d='LiDAR',
+        backend_args=backend_args))
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=1,
+    sampler=dict(type=DefaultSampler, shuffle=False),
+    dataset=dict(
+        type=KittiDataset,
+        data_root=data_root,
+        ann_file='kitti_infos_val.pkl',
+        modality=modality,
+        data_prefix=dict(
+            pts='training/velodyne_reduced', img='training/image_2'),
+        pipeline=test_pipeline,
+        metainfo=metainfo,
+        test_mode=True,
+        box_type_3d='LiDAR',
+        backend_args=backend_args))
+
+optim_wrapper.merge(
+    dict(
+        optimizer=dict(weight_decay=0.01),
+        clip_grad=dict(max_norm=35, norm_type=2),
+    ))
+val_evaluator = dict(
+    type=KittiMetric, ann_file='data/kitti/kitti_infos_val.pkl')
+test_evaluator = val_evaluator
+
+vis_backends = [dict(type=LocalVisBackend)]
+visualizer = dict(
+    type=Det3DLocalVisualizer, vis_backends=vis_backends, name='visualizer')
+
+# You may need to download the model first is the network is unstable
+load_from = 'https://download.openmmlab.com/mmdetection3d/pretrain_models/mvx_faster_rcnn_detectron2-caffe_20e_coco-pretrain_gt-sample_kitti-3-class_moderate-79.3_20200207-a4a6a3c7.pth'  # noqa

mmdet3d/configs/pgd/__init__.py

+# Copyright (c) OpenMMLab. All rights reserved.

mmdet3d/configs/pgd/pgd_r101_caffe_fpn_head_gn_4xb3_4x_kitti_mono3d.py

+# Copyright (c) OpenMMLab. All rights reserved.
+if '_base_':
+    from .._base_.datasets.kitti_mono3d import *
+    from .._base_.models.pgd import *
+    from .._base_.schedules.mmdet_schedule_1x import *
+    from .._base_.default_runtime import *
+
+from mmcv.transforms.processing import Resize
+from mmengine.optim.scheduler.lr_scheduler import LinearLR, MultiStepLR
+
+from mmdet3d.datasets.transforms.formating import Pack3DDetInputs
+from mmdet3d.datasets.transforms.loading import (LoadAnnotations3D,
+                                                 LoadImageFromFileMono3D)
+from mmdet3d.datasets.transforms.transforms_3d import RandomFlip3D
+from mmdet3d.models.data_preprocessors.data_preprocessor import \
+    Det3DDataPreprocessor
+from mmdet3d.models.losses.uncertain_smooth_l1_loss import \
+    UncertainSmoothL1Loss
+from mmdet3d.models.task_modules.coders.pgd_bbox_coder import PGDBBoxCoder
+
+# model settings
+model.merge(
+    dict(
+        data_preprocessor=dict(
+            type=Det3DDataPreprocessor,
+            mean=[103.530, 116.280, 123.675],
+            std=[1.0, 1.0, 1.0],
+            bgr_to_rgb=False,
+            pad_size_divisor=32),
+        backbone=dict(frozen_stages=0),
+        neck=dict(start_level=0, num_outs=4),
+        bbox_head=dict(
+            num_classes=3,
+            bbox_code_size=7,
+            pred_attrs=False,
+            pred_velo=False,
+            pred_bbox2d=True,
+            use_onlyreg_proj=True,
+            strides=(4, 8, 16, 32),
+            regress_ranges=((-1, 64), (64, 128), (128, 256), (256, 1e8)),
+            group_reg_dims=(2, 1, 3, 1, 16,
+                            4),  # offset, depth, size, rot, kpts, bbox2d
+            reg_branch=(
+                (256, ),  # offset
+                (256, ),  # depth
+                (256, ),  # size
+                (256, ),  # rot
+                (256, ),  # kpts
+                (256, )  # bbox2d
+            ),
+            centerness_branch=(256, ),
+            loss_cls=dict(
+                type='mmdet.FocalLoss',
+                use_sigmoid=True,
+                gamma=2.0,
+                alpha=0.25,
+                loss_weight=1.0),
+            loss_bbox=dict(
+                type='mmdet.SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0),
+            loss_dir=dict(
+                type='mmdet.CrossEntropyLoss',
+                use_sigmoid=False,
+                loss_weight=1.0),
+            loss_centerness=dict(
+                type='mmdet.CrossEntropyLoss',
+                use_sigmoid=True,
+                loss_weight=1.0),
+            use_depth_classifier=True,
+            depth_branch=(256, ),
+            depth_range=(0, 70),
+            depth_unit=10,
+            division='uniform',
+            depth_bins=8,
+            pred_keypoints=True,
+            weight_dim=1,
+            loss_depth=dict(
+                type=UncertainSmoothL1Loss,
+                alpha=1.0,
+                beta=3.0,
+                loss_weight=1.0),
+            bbox_coder=dict(
+                type=PGDBBoxCoder,
+                base_depths=((28.01, 16.32), ),
+                base_dims=((0.8, 1.73, 0.6), (1.76, 1.73, 0.6), (3.9, 1.56,
+                                                                 1.6)),
+                code_size=7)),
+        # set weight 1.0 for base 7 dims (offset, depth, size, rot)
+        # 0.2 for 16-dim keypoint offsets and 1.0 for 4-dim 2D distance targets
+        train_cfg=dict(code_weight=[
+            1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2,
+            0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 1.0, 1.0, 1.0,
+            1.0
+        ]),
+        test_cfg=dict(
+            nms_pre=100, nms_thr=0.05, score_thr=0.001, max_per_img=20)))
+
+backend_args = None
+
+train_pipeline = [
+    dict(type=LoadImageFromFileMono3D, backend_args=backend_args),
+    dict(
+        type=LoadAnnotations3D,
+        with_bbox=True,
+        with_label=True,
+        with_attr_label=False,
+        with_bbox_3d=True,
+        with_label_3d=True,
+        with_bbox_depth=True),
+    dict(type=Resize, scale=(1242, 375), keep_ratio=True),
+    dict(type=RandomFlip3D, flip_ratio_bev_horizontal=0.5),
+    dict(
+        type=Pack3DDetInputs,
+        keys=[
+            'img', 'gt_bboxes', 'gt_bboxes_labels', 'gt_bboxes_3d',
+            'gt_labels_3d', 'centers_2d', 'depths'
+        ]),
+]
+test_pipeline = [
+    dict(type=LoadImageFromFileMono3D, backend_args=backend_args),
+    dict(type=Resize, scale_factor=1.0),
+    dict(type=Pack3DDetInputs, keys=['img'])
+]
+
+train_dataloader.merge(
+    dict(batch_size=3, num_workers=3, dataset=dict(pipeline=train_pipeline)))
+test_dataloader.merge(dict(dataset=dict(pipeline=test_pipeline)))
+val_dataloader.merge(dict(dataset=dict(pipeline=test_pipeline)))
+
+# optimizer
+optim_wrapper.merge(
+    dict(
+        optimizer=dict(lr=0.001),
+        paramwise_cfg=dict(bias_lr_mult=2., bias_decay_mult=0.),
+        clip_grad=dict(max_norm=35, norm_type=2)))
+
+# learning rate
+param_scheduler = [
+    dict(
+        type=LinearLR, start_factor=1.0 / 3, by_epoch=False, begin=0, end=500),
+    dict(
+        type=MultiStepLR,
+        begin=0,
+        end=48,
+        by_epoch=True,
+        milestones=[32, 44],
+        gamma=0.1)
+]
+
+train_cfg.merge(dict(max_epochs=48, val_interval=2))
+auto_scale_lr.merge(dict(base_batch_size=12))

mmdet3d/configs/votenet/__init__.py

+# Copyright (c) OpenMMLab. All rights reserved.

mmdet3d/configs/votenet/votenet_8xb8_scannet_3d.py

+# Copyright (c) OpenMMLab. All rights reserved.
+if '_base_':
+    from .._base_.datasets.scannet_3d import *
+    from .._base_.models.votenet import *
+    from .._base_.schedules.schedule_3x import *
+    from .._base_.default_runtime import *
+
+from mmengine.hooks.logger_hook import LoggerHook
+
+from mmdet3d.models.task_modules.coders.partial_bin_based_bbox_coder import \
+    PartialBinBasedBBoxCoder
+
+# model settings
+model.merge(
+    dict(
+        bbox_head=dict(
+            num_classes=18,
+            bbox_coder=dict(
+                type=PartialBinBasedBBoxCoder,
+                num_sizes=18,
+                num_dir_bins=1,
+                with_rot=False,
+                mean_sizes=[[0.76966727, 0.8116021, 0.92573744],
+                            [1.876858, 1.8425595, 1.1931566],
+                            [0.61328, 0.6148609, 0.7182701],
+                            [1.3955007, 1.5121545, 0.83443564],
+                            [0.97949594, 1.0675149, 0.6329687],
+                            [0.531663, 0.5955577, 1.7500148],
+                            [0.9624706, 0.72462326, 1.1481868],
+                            [0.83221924, 1.0490936, 1.6875663],
+                            [0.21132214, 0.4206159, 0.5372846],
+                            [1.4440073, 1.8970833, 0.26985747],
+                            [1.0294262, 1.4040797, 0.87554324],
+                            [1.3766412, 0.65521795, 1.6813129],
+                            [0.6650819, 0.71111923, 1.298853],
+                            [0.41999173, 0.37906948, 1.7513971],
+                            [0.59359556, 0.5912492, 0.73919016],
+                            [0.50867593, 0.50656086, 0.30136237],
+                            [1.1511526, 1.0546296, 0.49706793],
+                            [0.47535285, 0.49249494, 0.5802117]]))))
+
+default_hooks.merge(dict(logger=dict(type=LoggerHook, interval=30)))
+# Default setting for scaling LR automatically
+#   - `enable` means enable scaling LR automatically
+#       or not by default.
+#   - `base_batch_size` = (8 GPUs) x (8 samples per GPU).
+auto_scale_lr.merge(dict(enable=False, base_batch_size=64))

setup.cfg

@@ -14,3 +14,6 @@ default_section = THIRDPARTY
 
 [codespell]
 ignore-words-list = ans,refridgerator,crate,hist,formating,dout,wan,nd,fo,avod,AVOD,warmup
+
+[flake8]
+per-file-ignores = mmdet3d/configs/*:F401,F403,F405