Release v1.1.0rc1

Release v1.1.0rc1

.circleci/test.yml

@@ -36,8 +36,6 @@ jobs:
         type: string
       torchvision:
         type: string
-      mmcv:
-        type: string
     docker:
       - image: cimg/python:<< parameters.python >>
     resource_class: large
@@ -62,7 +60,8 @@ jobs:
           name: Install mmdet3d dependencies
           command: |
             python -m pip install git+ssh://git@github.com/open-mmlab/mmengine.git@main
-            python -m pip install << parameters.mmcv >>
+            python -m pip install -U openmim
+            python -m mim install 'mmcv >= 2.0.0rc1'
             python -m pip install git+ssh://git@github.com/open-mmlab/mmdetection.git@dev-3.x
             python -m pip install -r requirements.txt
       - run:
@@ -85,8 +84,6 @@ jobs:
       cudnn:
         type: integer
         default: 7
-      mmcv:
-        type: string
     machine:
       image: ubuntu-2004-cuda-11.4:202110-01
       # docker_layer_caching: true
@@ -108,7 +105,8 @@ jobs:
           name: Install mmdet3d dependencies
           command: |
             docker exec mmdet3d pip install -e /mmengine
-            docker exec mmdet3d pip install << parameters.mmcv >>
+            docker exec mmdet3d pip install -U openmim
+            docker exec mmdet3d mim install 'mmcv >= 2.0.0rc1'
             docker exec mmdet3d pip install -e /mmdetection
             docker exec mmdet3d pip install -r requirements.txt
       - run:
@@ -144,8 +142,7 @@ workflows:
           name: minimum_version_cpu
           torch: 1.6.0
           torchvision: 0.7.0
-          python: 3.6.9  # The lowest python 3.6.x version available on CircleCI images
-          mmcv: https://download.openmmlab.com/mmcv/dev-2.x/cpu/torch1.6.0/mmcv_full-2.0.0rc0-cp36-cp36m-manylinux1_x86_64.whl
+          python: 3.7.4
           requires:
             - lint
       - build_cpu:
@@ -153,7 +150,6 @@ workflows:
           torch: 1.9.0
           torchvision: 0.10.0
           python: 3.9.0
-          mmcv: https://download.openmmlab.com/mmcv/dev-2.x/cpu/torch1.9.0/mmcv_full-2.0.0rc0-cp39-cp39-manylinux1_x86_64.whl
           requires:
             - minimum_version_cpu
       - hold:
@@ -166,7 +162,6 @@ workflows:
           # Use double quotation mark to explicitly specify its type
           # as string instead of number
           cuda: "10.2"
-          mmcv: https://download.openmmlab.com/mmcv/dev-2.x/cu102/torch1.8.0/mmcv_full-2.0.0rc0-cp37-cp37m-manylinux1_x86_64.whl
           requires:
             - hold
   merge_stage_test:
@@ -179,7 +174,6 @@ workflows:
           torch: 1.6.0
           # Use double quotation mark to explicitly specify its type
           # as string instead of number
-          mmcv: https://download.openmmlab.com/mmcv/dev-2.x/cu101/torch1.6.0/mmcv_full-2.0.0rc0-cp37-cp37m-manylinux1_x86_64.whl
           cuda: "10.1"
           filters:
             branches:

.gitignore

@@ -133,3 +133,4 @@ data/sunrgbd/OFFICIAL_SUNRGBD/
 
 # Waymo evaluation
 mmdet3d/core/evaluation/waymo_utils/compute_detection_metrics_main
+mmdet3d/core/evaluation/waymo_utils/compute_detection_let_metrics_main

.pre-commit-config.yaml

 repos:
   - repo: https://github.com/PyCQA/flake8
-    rev: 3.8.3
+    rev: 5.0.4
     hooks:
       - id: flake8
   - repo: https://github.com/PyCQA/isort
@@ -8,11 +8,11 @@ repos:
     hooks:
       - id: isort
   - repo: https://github.com/pre-commit/mirrors-yapf
-    rev: v0.30.0
+    rev: v0.32.0
     hooks:
       - id: yapf
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v3.1.0
+    rev: v4.3.0
     hooks:
       - id: trailing-whitespace
       - id: check-yaml
@@ -25,7 +25,7 @@ repos:
       - id: mixed-line-ending
         args: ["--fix=lf"]
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.1.0
+    rev: v2.2.1
     hooks:
       - id: codespell
   - repo: https://github.com/executablebooks/mdformat

README.md

@@ -82,9 +82,7 @@ This project is released under the [Apache 2.0 license](LICENSE).
 
 ## Changelog
 
-We are excited to announce the release of MMDetection3D 1.1.0rc0.
-
-MMDet3D 1.1 unifies the interfaces of dataset, models, evaluation, and visualization with faster training and testing speed.
+**1.1.0rc1** was released in 11/10/2022.
 
 Please refer to [changelog.md](docs/en/notes/changelog.md) for details and release history.
 

README_zh-CN.md

@@ -82,7 +82,7 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱, 下一代
 
 ## 更新日志
 
-MMDetection3D 1.1.0rc0，MMDet3D 在 OpenMMLab 2.0 项目中的首个版本发布。
+我们在 2022.10.11 发布了 **1.1.0rc1** 版本.
 
 更多细节和版本发布历史可以参考[changelog.md](docs/en/notes/changelog.md).
 

configs/_base_/datasets/kitti-3d-3class.py

@@ -67,7 +67,7 @@ test_pipeline = [
 # please keep its loading function consistent with test_pipeline (e.g. client)
 eval_pipeline = [
     dict(type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4),
-    dict(type='Pack3DDetInputs', keys=['points']),
+    dict(type='Pack3DDetInputs', keys=['points'])
 ]
 train_dataloader = dict(
     batch_size=6,
@@ -126,3 +126,7 @@ val_evaluator = dict(
     ann_file=data_root + 'kitti_infos_val.pkl',
     metric='bbox')
 test_evaluator = val_evaluator
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='Det3DLocalVisualizer', vis_backends=vis_backends, name='visualizer')

configs/_base_/datasets/kitti-3d-car.py

@@ -124,3 +124,7 @@ val_evaluator = dict(
     ann_file=data_root + 'kitti_infos_val.pkl',
     metric='bbox')
 test_evaluator = val_evaluator
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='Det3DLocalVisualizer', vis_backends=vis_backends, name='visualizer')

configs/_base_/datasets/kitti-mono3d.py

@@ -35,6 +35,10 @@ test_pipeline = [
     dict(type='Resize', scale=(1242, 375), keep_ratio=True),
     dict(type='Pack3DDetInputs', keys=['img'])
 ]
+eval_pipeline = [
+    dict(type='LoadImageFromFileMono3D'),
+    dict(type='Pack3DDetInputs', keys=['img'])
+]
 
 train_dataloader = dict(
     batch_size=2,
@@ -78,3 +82,7 @@ val_evaluator = dict(
     pred_box_type_3d='Camera')
 
 test_evaluator = val_evaluator
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='Det3DLocalVisualizer', vis_backends=vis_backends, name='visualizer')

configs/_base_/datasets/lyft-3d.py

@@ -124,3 +124,7 @@ test_evaluator = dict(
     type='LyftMetric',
     ann_file=data_root + 'lyft_infos_val.pkl',
     metric='bbox')
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='Det3DLocalVisualizer', vis_backends=vis_backends, name='visualizer')

configs/_base_/datasets/nus-3d.py

@@ -126,3 +126,7 @@ val_evaluator = dict(
     ann_file=data_root + 'nuscenes_infos_val.pkl',
     metric='bbox')
 test_evaluator = val_evaluator
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='Det3DLocalVisualizer', vis_backends=vis_backends, name='visualizer')

configs/_base_/datasets/nus-mono3d.py

@@ -65,7 +65,7 @@ train_dataloader = dict(
             CAM_BACK_RIGHT='samples/CAM_BACK_RIGHT',
             CAM_BACK_LEFT='samples/CAM_BACK_LEFT'),
         ann_file='nuscenes_infos_train.pkl',
-        task='mono3d',
+        task='mono_det',
         pipeline=train_pipeline,
         metainfo=metainfo,
         modality=input_modality,
@@ -92,7 +92,7 @@ val_dataloader = dict(
             CAM_BACK_RIGHT='samples/CAM_BACK_RIGHT',
             CAM_BACK_LEFT='samples/CAM_BACK_LEFT'),
         ann_file='nuscenes_infos_val.pkl',
-        task='mono3d',
+        task='mono_det',
         pipeline=test_pipeline,
         modality=input_modality,
         metainfo=metainfo,
@@ -108,3 +108,7 @@ val_evaluator = dict(
     metric='bbox')
 
 test_evaluator = val_evaluator
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='Det3DLocalVisualizer', vis_backends=vis_backends, name='visualizer')

configs/_base_/datasets/s3dis-seg.py

@@ -142,3 +142,7 @@ val_dataloader = test_dataloader
 
 val_evaluator = dict(type='SegMetric')
 test_evaluator = val_evaluator
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='Det3DLocalVisualizer', vis_backends=vis_backends, name='visualizer')

configs/_base_/datasets/scannet-3d.py

@@ -125,3 +125,7 @@ test_dataloader = dict(
         box_type_3d='Depth'))
 val_evaluator = dict(type='IndoorMetric')
 test_evaluator = val_evaluator
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='Det3DLocalVisualizer', vis_backends=vis_backends, name='visualizer')

configs/_base_/datasets/scannet-seg.py

@@ -137,3 +137,7 @@ val_dataloader = test_dataloader
 
 val_evaluator = dict(type='SegMetric')
 test_evaluator = val_evaluator
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='Det3DLocalVisualizer', vis_backends=vis_backends, name='visualizer')

configs/_base_/datasets/sunrgbd-3d.py

@@ -111,3 +111,7 @@ test_dataloader = dict(
         box_type_3d='Depth'))
 val_evaluator = dict(type='IndoorMetric')
 test_evaluator = val_evaluator
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='Det3DLocalVisualizer', vis_backends=vis_backends, name='visualizer')

configs/_base_/datasets/waymoD5-3d-3class.py

@@ -2,13 +2,18 @@
 # D5 in the config name means the whole dataset is divided into 5 folds
 # We only use one fold for efficient experiments
 dataset_type = 'WaymoDataset'
+# data_root = 's3://openmmlab/datasets/detection3d/waymo/kitti_format/'
 data_root = 'data/waymo/kitti_format/'
 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='s3://waymo_data/'))
+#     backend='petrel',
+#     path_mapping={
+#         './data/waymo': 's3://openmmlab/datasets/detection3d/waymo',
+#         'data/waymo': 's3://openmmlab/datasets/detection3d/waymo'
+#     })
 
 class_names = ['Car', 'Pedestrian', 'Cyclist']
 metainfo = dict(CLASSES=class_names)
@@ -33,7 +38,7 @@ db_sampler = dict(
 train_pipeline = [
     dict(type='LoadPointsFromFile', coord_type='LIDAR', load_dim=6, use_dim=5),
     dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
-    dict(type='ObjectSample', db_sampler=db_sampler),
+    # dict(type='ObjectSample', db_sampler=db_sampler),
     dict(
         type='RandomFlip3D',
         sync_2d=False,
@@ -51,7 +56,12 @@ train_pipeline = [
         keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
 ]
 test_pipeline = [
-    dict(type='LoadPointsFromFile', coord_type='LIDAR', load_dim=6, use_dim=5),
+    dict(
+        type='LoadPointsFromFile',
+        coord_type='LIDAR',
+        load_dim=6,
+        use_dim=5,
+        file_client_args=file_client_args),
     dict(
         type='MultiScaleFlipAug3D',
         img_scale=(1333, 800),
@@ -88,7 +98,8 @@ train_dataloader = dict(
             type=dataset_type,
             data_root=data_root,
             ann_file='waymo_infos_train.pkl',
-            data_prefix=dict(pts='training/velodyne'),
+            data_prefix=dict(
+                pts='training/velodyne', sweeps='training/velodyne'),
             pipeline=train_pipeline,
             modality=input_modality,
             test_mode=False,
@@ -97,7 +108,8 @@ train_dataloader = dict(
             # and box_type_3d='Depth' in sunrgbd and scannet dataset.
             box_type_3d='LiDAR',
             # load one frame every five frames
-            load_interval=5)))
+            load_interval=5,
+            file_client_args=file_client_args)))
 val_dataloader = dict(
     batch_size=1,
     num_workers=1,
@@ -107,13 +119,14 @@ val_dataloader = dict(
     dataset=dict(
         type=dataset_type,
         data_root=data_root,
-        data_prefix=dict(pts='training/velodyne'),
+        data_prefix=dict(pts='training/velodyne', sweeps='training/velodyne'),
         ann_file='waymo_infos_val.pkl',
         pipeline=eval_pipeline,
         modality=input_modality,
         test_mode=True,
         metainfo=metainfo,
-        box_type_3d='LiDAR'))
+        box_type_3d='LiDAR',
+        file_client_args=file_client_args))
 
 test_dataloader = dict(
     batch_size=1,
@@ -124,17 +137,23 @@ test_dataloader = dict(
     dataset=dict(
         type=dataset_type,
         data_root=data_root,
-        data_prefix=dict(pts='training/velodyne'),
+        data_prefix=dict(pts='training/velodyne', sweeps='training/velodyne'),
         ann_file='waymo_infos_val.pkl',
         pipeline=eval_pipeline,
         modality=input_modality,
         test_mode=True,
         metainfo=metainfo,
-        box_type_3d='LiDAR'))
+        box_type_3d='LiDAR',
+        file_client_args=file_client_args))
 
 val_evaluator = dict(
     type='WaymoMetric',
     ann_file='./data/waymo/kitti_format/waymo_infos_val.pkl',
     waymo_bin_file='./data/waymo/waymo_format/gt.bin',
-    data_root='./data/waymo/waymo_format')
+    data_root='./data/waymo/waymo_format',
+    file_client_args=file_client_args)
 test_evaluator = val_evaluator
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='Det3DLocalVisualizer', vis_backends=vis_backends, name='visualizer')

configs/_base_/datasets/waymoD5-3d-car.py

@@ -86,7 +86,8 @@ train_dataloader = dict(
             type=dataset_type,
             data_root=data_root,
             ann_file='waymo_infos_train.pkl',
-            data_prefix=dict(pts='training/velodyne'),
+            data_prefix=dict(
+                pts='training/velodyne', sweeps='training/velodyne'),
             pipeline=train_pipeline,
             modality=input_modality,
             test_mode=False,
@@ -105,7 +106,7 @@ val_dataloader = dict(
     dataset=dict(
         type=dataset_type,
         data_root=data_root,
-        data_prefix=dict(pts='training/velodyne'),
+        data_prefix=dict(pts='training/velodyne', sweeps='training/velodyne'),
         ann_file='waymo_infos_val.pkl',
         pipeline=eval_pipeline,
         modality=input_modality,
@@ -122,7 +123,7 @@ test_dataloader = dict(
     dataset=dict(
         type=dataset_type,
         data_root=data_root,
-        data_prefix=dict(pts='training/velodyne'),
+        data_prefix=dict(pts='training/velodyne', sweeps='training/velodyne'),
         ann_file='waymo_infos_val.pkl',
         pipeline=eval_pipeline,
         modality=input_modality,
@@ -136,3 +137,7 @@ val_evaluator = dict(
     waymo_bin_file='./data/waymo/waymo_format/gt.bin',
     data_root='./data/waymo/waymo_format')
 test_evaluator = val_evaluator
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='Det3DLocalVisualizer', vis_backends=vis_backends, name='visualizer')

configs/_base_/datasets/waymoD5-mono3d-3class.py

+# dataset settings
+# D3 in the config name means the whole dataset is divided into 3 folds
+# We only use one fold for efficient experiments
+dataset_type = 'WaymoDataset'
+data_root = 'data/waymo/kitti_format/'
+class_names = ['Car', 'Pedestrian', 'Cyclist']
+input_modality = dict(use_lidar=False, use_camera=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.
+train_pipeline = [
+    dict(type='LoadImageFromFileMono3D'),
+    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),
+    # base shape (1248, 832), scale (0.95, 1.05)
+    dict(
+        type='RandomResize3D',
+        scale=(1284, 832),
+        ratio_range=(0.95, 1.05),
+        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'),
+    dict(
+        type='RandomResize3D',
+        scale=(1248, 832),
+        ratio_range=(1., 1.),
+        keep_ratio=True),
+    dict(type='Pack3DDetInputs', keys=['img']),
+]
+# 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='LoadImageFromFileMono3D'),
+    dict(
+        type='RandomResize3D',
+        scale=(1248, 832),
+        ratio_range=(1., 1.),
+        keep_ratio=True),
+    dict(type='Pack3DDetInputs', keys=['img']),
+]
+
+metainfo = dict(CLASSES=class_names)
+
+train_dataloader = dict(
+    batch_size=3,
+    num_workers=3,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='waymo_infos_train.pkl',
+        data_prefix=dict(
+            pts='training/velodyne',
+            CAM_FRONT='training/image_0',
+            CAM_FRONT_RIGHT='training/image_1',
+            CAM_FRONT_LEFT='training/image_2',
+            CAM_SIDE_RIGHT='training/image_3',
+            CAM_SIDE_LEFT='training/image_4'),
+        pipeline=train_pipeline,
+        modality=input_modality,
+        test_mode=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='Camera',
+        task='mono3d',
+        # load one frame every three frames
+        load_interval=5))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=1,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            pts='training/velodyne',
+            CAM_FRONT='training/image_0',
+            CAM_FRONT_RIGHT='training/image_1',
+            CAM_FRONT_LEFT='training/image_2',
+            CAM_SIDE_RIGHT='training/image_3',
+            CAM_SIDE_LEFT='training/image_4'),
+        ann_file='waymo_infos_val.pkl',
+        pipeline=eval_pipeline,
+        modality=input_modality,
+        test_mode=True,
+        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='Camera',
+        task='mono3d',
+    ))
+
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=1,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            pts='training/velodyne',
+            CAM_FRONT='training/image_0',
+            CAM_FRONT_RIGHT='training/image_1',
+            CAM_FRONT_LEFT='training/image_2',
+            CAM_SIDE_RIGHT='training/image_3',
+            CAM_SIDE_LEFT='training/image_4'),
+        ann_file='waymo_infos_val.pkl',
+        pipeline=eval_pipeline,
+        modality=input_modality,
+        test_mode=True,
+        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='Camera',
+        task='mono3d',
+    ))
+
+val_evaluator = dict(
+    type='WaymoMetric',
+    ann_file='./data/waymo/kitti_format/waymo_infos_val.pkl',
+    waymo_bin_file='./data/waymo/waymo_format/cam_gt.bin',
+    data_root='./data/waymo/waymo_format',
+    metric='LET_mAP',
+    task='mono3d')
+test_evaluator = val_evaluator

configs/_base_/datasets/waymoD5-mv3d-3class.py

+# dataset settings
+# D3 in the config name means the whole dataset is divided into 3 folds
+# We only use one fold for efficient experiments
+dataset_type = 'WaymoDataset'
+data_root = 'data/waymo/kitti_format/'
+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.
+
+class_names = ['Car', 'Pedestrian', 'Cyclist']
+input_modality = dict(use_lidar=False, use_camera=True)
+point_cloud_range = [-35.0, -75.0, -2, 75.0, 75.0, 4]
+
+train_transforms = [
+    dict(type='PhotoMetricDistortion3D'),
+    dict(
+        type='RandomResize3D',
+        scale=(1248, 832),
+        ratio_range=(0.95, 1.05),
+        keep_ratio=True),
+    dict(type='RandomCrop3D', crop_size=(720, 1080)),
+    dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5, flip_box3d=False),
+]
+
+train_pipeline = [
+    dict(type='LoadMultiViewImageFromFiles', to_float32=True),
+    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='MultiViewWrapper', transforms=train_transforms),
+    dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
+    dict(type='ObjectNameFilter', classes=class_names),
+    dict(
+        type='Pack3DDetInputs', keys=[
+            'img',
+            'gt_bboxes_3d',
+            'gt_labels_3d',
+        ]),
+]
+test_transforms = [
+    dict(
+        type='RandomResize3D',
+        scale=(1248, 832),
+        ratio_range=(1., 1.),
+        keep_ratio=True)
+]
+test_pipeline = [
+    dict(type='LoadMultiViewImageFromFiles', to_float32=True),
+    dict(type='MultiViewWrapper', transforms=test_transforms),
+    dict(type='Pack3DDetInputs', keys=['img'])
+]
+# 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='LoadMultiViewImageFromFiles', to_float32=True),
+    dict(type='MultiViewWrapper', transforms=test_transforms),
+    dict(type='Pack3DDetInputs', keys=['img'])
+]
+metainfo = dict(CLASSES=class_names)
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='waymo_infos_train.pkl',
+        data_prefix=dict(
+            pts='training/velodyne',
+            CAM_FRONT='training/image_0',
+            CAM_FRONT_RIGHT='training/image_1',
+            CAM_FRONT_LEFT='training/image_2',
+            CAM_SIDE_RIGHT='training/image_3',
+            CAM_SIDE_LEFT='training/image_4',
+        ),
+        pipeline=train_pipeline,
+        modality=input_modality,
+        test_mode=False,
+        metainfo=metainfo,
+        box_type_3d='Lidar',
+        load_interval=5,
+    ))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=1,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='waymo_infos_val.pkl',
+        data_prefix=dict(
+            pts='training/velodyne',
+            CAM_FRONT='training/image_0',
+            CAM_FRONT_RIGHT='training/image_1',
+            CAM_FRONT_LEFT='training/image_2',
+            CAM_SIDE_RIGHT='training/image_3',
+            CAM_SIDE_LEFT='training/image_4',
+        ),
+        pipeline=eval_pipeline,
+        modality=input_modality,
+        test_mode=True,
+        metainfo=metainfo,
+        box_type_3d='Lidar',
+    ))
+
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=1,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='waymo_infos_val.pkl',
+        data_prefix=dict(
+            pts='training/velodyne',
+            CAM_FRONT='training/image_0',
+            CAM_FRONT_RIGHT='training/image_1',
+            CAM_FRONT_LEFT='training/image_2',
+            CAM_SIDE_RIGHT='training/image_3',
+            CAM_SIDE_LEFT='training/image_4',
+        ),
+        pipeline=eval_pipeline,
+        modality=input_modality,
+        test_mode=True,
+        metainfo=metainfo,
+        box_type_3d='Lidar',
+    ))
+val_evaluator = dict(
+    type='WaymoMetric',
+    ann_file='./data/waymo/kitti_format/waymo_infos_val.pkl',
+    waymo_bin_file='./data/waymo/waymo_format/cam_gt.bin',
+    data_root='./data/waymo/waymo_format',
+    metric='LET_mAP')
+
+test_evaluator = val_evaluator