将子模块转换为普通目录

docker-hub/MapTRv2/MapTR/projects/configs/_base_/schedules/seg_cosine_150e.py

+# optimizer
+# This schedule is mainly used on S3DIS dataset in segmentation task
+optimizer = dict(type='SGD', lr=0.2, weight_decay=0.0001, momentum=0.9)
+optimizer_config = dict(grad_clip=None)
+lr_config = dict(policy='CosineAnnealing', warmup=None, min_lr=0.002)
+momentum_config = None
+
+# runtime settings
+runner = dict(type='EpochBasedRunner', max_epochs=150)

docker-hub/MapTRv2/MapTR/projects/configs/_base_/schedules/seg_cosine_200e.py

+# optimizer
+# This schedule is mainly used on ScanNet dataset in segmentation task
+optimizer = dict(type='Adam', lr=0.001, weight_decay=0.01)
+optimizer_config = dict(grad_clip=None)
+lr_config = dict(policy='CosineAnnealing', warmup=None, min_lr=1e-5)
+momentum_config = None
+
+# runtime settings
+runner = dict(type='EpochBasedRunner', max_epochs=200)

docker-hub/MapTRv2/MapTR/projects/configs/_base_/schedules/seg_cosine_50e.py

+# optimizer
+# This schedule is mainly used on S3DIS dataset in segmentation task
+optimizer = dict(type='Adam', lr=0.001, weight_decay=0.001)
+optimizer_config = dict(grad_clip=None)
+lr_config = dict(policy='CosineAnnealing', warmup=None, min_lr=1e-5)
+momentum_config = None
+
+# runtime settings
+runner = dict(type='EpochBasedRunner', max_epochs=50)

docker-hub/MapTRv2/MapTR/projects/configs/bevformer/bevformer_base.py

+_base_ = [
+    '../datasets/custom_nus-3d.py',
+    '../_base_/default_runtime.py'
+]
+#
+plugin = True
+plugin_dir = 'projects/mmdet3d_plugin/'
+
+# 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]
+voxel_size = [0.2, 0.2, 8]
+
+
+
+img_norm_cfg = dict(
+    mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
+# For nuScenes we usually do 10-class detection
+class_names = [
+    'car', 'truck', 'construction_vehicle', 'bus', 'trailer', 'barrier',
+    'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone'
+]
+
+input_modality = dict(
+    use_lidar=False,
+    use_camera=True,
+    use_radar=False,
+    use_map=False,
+    use_external=True)
+
+_dim_ = 256
+_pos_dim_ = _dim_//2
+_ffn_dim_ = _dim_*2
+_num_levels_ = 4
+bev_h_ = 200
+bev_w_ = 200
+queue_length = 4 # each sequence contains `queue_length` frames.
+
+model = dict(
+    type='BEVFormer',
+    use_grid_mask=True,
+    video_test_mode=True,
+    img_backbone=dict(
+        type='ResNet',
+        depth=101,
+        num_stages=4,
+        out_indices=(1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN2d', requires_grad=False),
+        norm_eval=True,
+        style='caffe',
+        dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False), # original DCNv2 will print log when perform load_state_dict
+        stage_with_dcn=(False, False, True, True)),
+    img_neck=dict(
+        type='FPN',
+        in_channels=[512, 1024, 2048],
+        out_channels=_dim_,
+        start_level=0,
+        add_extra_convs='on_output',
+        num_outs=4,
+        relu_before_extra_convs=True),
+    pts_bbox_head=dict(
+        type='BEVFormerHead',
+        bev_h=bev_h_,
+        bev_w=bev_w_,
+        num_query=900,
+        num_classes=10,
+        in_channels=_dim_,
+        sync_cls_avg_factor=True,
+        with_box_refine=True,
+        as_two_stage=False,
+        transformer=dict(
+            type='PerceptionTransformer',
+            rotate_prev_bev=True,
+            use_shift=True,
+            use_can_bus=True,
+            embed_dims=_dim_,
+            encoder=dict(
+                type='BEVFormerEncoder',
+                num_layers=6,
+                pc_range=point_cloud_range,
+                num_points_in_pillar=4,
+                return_intermediate=False,
+                transformerlayers=dict(
+                    type='BEVFormerLayer',
+                    attn_cfgs=[
+                        dict(
+                            type='TemporalSelfAttention',
+                            embed_dims=_dim_,
+                            num_levels=1),
+                        dict(
+                            type='SpatialCrossAttention',
+                            pc_range=point_cloud_range,
+                            deformable_attention=dict(
+                                type='MSDeformableAttention3D',
+                                embed_dims=_dim_,
+                                num_points=8,
+                                num_levels=_num_levels_),
+                            embed_dims=_dim_,
+                        )
+                    ],
+                    feedforward_channels=_ffn_dim_,
+                    ffn_dropout=0.1,
+                    operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
+                                     'ffn', 'norm'))),
+            decoder=dict(
+                type='DetectionTransformerDecoder',
+                num_layers=6,
+                return_intermediate=True,
+                transformerlayers=dict(
+                    type='DetrTransformerDecoderLayer',
+                    attn_cfgs=[
+                        dict(
+                            type='MultiheadAttention',
+                            embed_dims=_dim_,
+                            num_heads=8,
+                            dropout=0.1),
+                         dict(
+                            type='CustomMSDeformableAttention',
+                            embed_dims=_dim_,
+                            num_levels=1),
+                    ],
+
+                    feedforward_channels=_ffn_dim_,
+                    ffn_dropout=0.1,
+                    operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
+                                     'ffn', 'norm')))),
+        bbox_coder=dict(
+            type='NMSFreeCoder',
+            post_center_range=[-61.2, -61.2, -10.0, 61.2, 61.2, 10.0],
+            pc_range=point_cloud_range,
+            max_num=300,
+            voxel_size=voxel_size,
+            num_classes=10),
+        positional_encoding=dict(
+            type='LearnedPositionalEncoding',
+            num_feats=_pos_dim_,
+            row_num_embed=bev_h_,
+            col_num_embed=bev_w_,
+            ),
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=2.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=0.25),
+        loss_iou=dict(type='GIoULoss', loss_weight=0.0)),
+    # model training and testing settings
+    train_cfg=dict(pts=dict(
+        grid_size=[512, 512, 1],
+        voxel_size=voxel_size,
+        point_cloud_range=point_cloud_range,
+        out_size_factor=4,
+        assigner=dict(
+            type='HungarianAssigner3D',
+            cls_cost=dict(type='FocalLossCost', weight=2.0),
+            reg_cost=dict(type='BBox3DL1Cost', weight=0.25),
+            iou_cost=dict(type='IoUCost', weight=0.0), # Fake cost. This is just to make it compatible with DETR head.
+            pc_range=point_cloud_range))))
+
+dataset_type = 'CustomNuScenesDataset'
+data_root = 'data/nuscenes/'
+file_client_args = dict(backend='disk')
+
+
+train_pipeline = [
+    dict(type='LoadMultiViewImageFromFiles', to_float32=True),
+    dict(type='PhotoMetricDistortionMultiViewImage'),
+    dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True, with_attr_label=False),
+    dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
+    dict(type='ObjectNameFilter', classes=class_names),
+    dict(type='NormalizeMultiviewImage', **img_norm_cfg),
+    dict(type='PadMultiViewImage', size_divisor=32),
+    dict(type='DefaultFormatBundle3D', class_names=class_names),
+    dict(type='CustomCollect3D', keys=['gt_bboxes_3d', 'gt_labels_3d', 'img'])
+]
+
+test_pipeline = [
+    dict(type='LoadMultiViewImageFromFiles', to_float32=True),
+    dict(type='NormalizeMultiviewImage', **img_norm_cfg),
+    dict(type='PadMultiViewImage', size_divisor=32),
+    dict(
+        type='MultiScaleFlipAug3D',
+        img_scale=(1600, 900),
+        pts_scale_ratio=1,
+        flip=False,
+        transforms=[
+            dict(
+                type='DefaultFormatBundle3D',
+                class_names=class_names,
+                with_label=False),
+            dict(type='CustomCollect3D', keys=['img'])
+        ])
+]
+
+data = dict(
+    samples_per_gpu=1,
+    workers_per_gpu=4,
+    train=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file=data_root + 'nuscenes_infos_temporal_train.pkl',
+        pipeline=train_pipeline,
+        classes=class_names,
+        modality=input_modality,
+        test_mode=False,
+        use_valid_flag=True,
+        bev_size=(bev_h_, bev_w_),
+        queue_length=queue_length,
+        # 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'),
+    val=dict(type=dataset_type,
+             data_root=data_root,
+             ann_file=data_root + 'nuscenes_infos_temporal_val.pkl',
+             pipeline=test_pipeline,  bev_size=(bev_h_, bev_w_),
+             classes=class_names, modality=input_modality, samples_per_gpu=1),
+    test=dict(type=dataset_type,
+              data_root=data_root,
+              ann_file=data_root + 'nuscenes_infos_temporal_val.pkl',
+              pipeline=test_pipeline, bev_size=(bev_h_, bev_w_),
+              classes=class_names, modality=input_modality),
+    shuffler_sampler=dict(type='DistributedGroupSampler'),
+    nonshuffler_sampler=dict(type='DistributedSampler')
+)
+
+optimizer = dict(
+    type='AdamW',
+    lr=2e-4,
+    paramwise_cfg=dict(
+        custom_keys={
+            'img_backbone': dict(lr_mult=0.1),
+        }),
+    weight_decay=0.01)
+
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='CosineAnnealing',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    min_lr_ratio=1e-3)
+total_epochs = 24
+evaluation = dict(interval=1, pipeline=test_pipeline)
+
+runner = dict(type='EpochBasedRunner', max_epochs=total_epochs)
+load_from = 'ckpts/r101_dcn_fcos3d_pretrain.pth'
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        dict(type='TensorboardLoggerHook')
+    ])
+
+checkpoint_config = dict(interval=1)

docker-hub/MapTRv2/MapTR/projects/configs/datasets/custom_lyft-3d.py

+# If point cloud range is changed, the models should also change their point
+# cloud range accordingly
+point_cloud_range = [-80, -80, -5, 80, 80, 3]
+# For Lyft we usually do 9-class detection
+class_names = [
+    'car', 'truck', 'bus', 'emergency_vehicle', 'other_vehicle', 'motorcycle',
+    'bicycle', 'pedestrian', 'animal'
+]
+dataset_type = 'CustomLyftDataset'
+data_root = 'data/lyft/'
+# Input modality for Lyft dataset, this is consistent with the submission
+# format which requires the information in input_modality.
+input_modality = dict(
+    use_lidar=True,
+    use_camera=False,
+    use_radar=False,
+    use_map=False,
+    use_external=True)
+file_client_args = dict(backend='disk')
+# Uncomment the following if use ceph or other file clients.
+# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
+# for more details.
+# file_client_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/lyft/': 's3://lyft/lyft/',
+#         'data/lyft/': 's3://lyft/lyft/'
+#    }))
+train_pipeline = [
+    dict(
+        type='LoadPointsFromFile',
+        coord_type='LIDAR',
+        load_dim=5,
+        use_dim=5,
+        file_client_args=file_client_args),
+    dict(
+        type='LoadPointsFromMultiSweeps',
+        sweeps_num=10,
+        file_client_args=file_client_args),
+    dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
+    dict(
+        type='GlobalRotScaleTrans',
+        rot_range=[-0.3925, 0.3925],
+        scale_ratio_range=[0.95, 1.05],
+        translation_std=[0, 0, 0]),
+    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='DefaultFormatBundle3D', class_names=class_names),
+    dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
+]
+test_pipeline = [
+    dict(
+        type='LoadPointsFromFile',
+        coord_type='LIDAR',
+        load_dim=5,
+        use_dim=5,
+        file_client_args=file_client_args),
+    dict(
+        type='LoadPointsFromMultiSweeps',
+        sweeps_num=10,
+        file_client_args=file_client_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='DefaultFormatBundle3D',
+                class_names=class_names,
+                with_label=False),
+            dict(type='Collect3D', keys=['points'])
+        ])
+]
+# construct a pipeline for data and gt loading in show function
+# please keep its loading function consistent with test_pipeline (e.g. client)
+eval_pipeline = [
+    dict(
+        type='LoadPointsFromFile',
+        coord_type='LIDAR',
+        load_dim=5,
+        use_dim=5,
+        file_client_args=file_client_args),
+    dict(
+        type='LoadPointsFromMultiSweeps',
+        sweeps_num=10,
+        file_client_args=file_client_args),
+    dict(
+        type='DefaultFormatBundle3D',
+        class_names=class_names,
+        with_label=False),
+    dict(type='Collect3D', keys=['points'])
+]
+
+data = dict(
+    samples_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file=data_root + 'lyft_infos_train.pkl',
+        pipeline=train_pipeline,
+        classes=class_names,
+        modality=input_modality,
+        test_mode=False),
+    val=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file=data_root + 'lyft_infos_val.pkl',
+        pipeline=test_pipeline,
+        classes=class_names,
+        modality=input_modality,
+        test_mode=True),
+    test=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file=data_root + 'lyft_infos_val.pkl',
+        pipeline=test_pipeline,
+        classes=class_names,
+        modality=input_modality,
+        test_mode=True))
+# For Lyft dataset, we usually evaluate the model at the end of training.
+# Since the models are trained by 24 epochs by default, we set evaluation
+# interval to be 24. Please change the interval accordingly if you do not
+# use a default schedule.
+evaluation = dict(interval=24, pipeline=eval_pipeline)
\ No newline at end of file