new file: projects/configs/datasets/custom_lyft-3d.py

	new file:   projects/configs/datasets/custom_nus-3d.py
	new file:   projects/configs/datasets/custom_waymo-3d.py

projects/configs/datasets/custom_lyft-3d.py

@@ -0,0 +1,136 @@
+# 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)

projects/configs/datasets/custom_nus-3d.py

@@ -0,0 +1,141 @@
+# If point cloud range is changed, the models should also change their point
+# cloud range accordingly
+point_cloud_range = [-50, -50, -5, 50, 50, 3]
+# For nuScenes we usually do 10-class detection
+class_names = [
+    'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
+    'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
+]
+dataset_type = 'NuScenesDataset_eval_modified'
+data_root = 'data/nuscenes/'
+# Input modality for nuScenes 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=False)
+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/nuscenes/': 's3://nuscenes/nuscenes/',
+#         'data/nuscenes/': 's3://nuscenes/nuscenes/'
+#     }))
+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='ObjectNameFilter', classes=class_names),
+    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=4,
+    workers_per_gpu=4,
+    train=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file=data_root + 'nuscenes_infos_train.pkl',
+        pipeline=train_pipeline,
+        classes=class_names,
+        modality=input_modality,
+        test_mode=False,
+        # 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,
+        ann_file=data_root + 'nuscenes_infos_val.pkl',
+        pipeline=test_pipeline,
+        classes=class_names,
+        modality=input_modality,
+        test_mode=True,
+        box_type_3d='LiDAR'),
+    test=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file=data_root + 'nuscenes_infos_val.pkl',
+        pipeline=test_pipeline,
+        classes=class_names,
+        modality=input_modality,
+        test_mode=True,
+        box_type_3d='LiDAR'))
+# For nuScenes 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)

projects/configs/datasets/custom_waymo-3d.py

@@ -0,0 +1,112 @@
+# dataset settings
+# D5 in the config name means the whole dataset is divided into 5 folds
+# We only use one fold for efficient experiments
+dataset_type = 'CustomWaymoDataset'
+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/'))
+
+img_norm_cfg = dict(
+    mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
+class_names = ['Car', 'Pedestrian', 'Cyclist']
+point_cloud_range = [-74.88, -74.88, -2, 74.88, 74.88, 4]
+input_modality = dict(use_lidar=False, use_camera=True)
+db_sampler = dict(
+    data_root=data_root,
+    info_path=data_root + 'waymo_dbinfos_train.pkl',
+    rate=1.0,
+    prepare=dict(
+        filter_by_difficulty=[-1],
+        filter_by_min_points=dict(Car=5, Pedestrian=10, Cyclist=10)),
+    classes=class_names,
+    sample_groups=dict(Car=15, Pedestrian=10, Cyclist=10),
+    points_loader=dict(
+        type='LoadPointsFromFile',
+        coord_type='LIDAR',
+        load_dim=5,
+        use_dim=[0, 1, 2, 3, 4],
+        file_client_args=file_client_args))
+
+
+
+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=(1920, 1280),
+        pts_scale_ratio=1,
+        flip=False,
+        transforms=[
+            dict(
+                type='DefaultFormatBundle3D',
+                class_names=class_names,
+                with_label=False),
+            dict(type='CustomCollect3D', 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)
+
+data = dict(
+    samples_per_gpu=2,
+    workers_per_gpu=4,
+    train=dict(
+        type='RepeatDataset',
+        times=2,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file=data_root + 'waymo_infos_train.pkl',
+            split='training',
+            pipeline=train_pipeline,
+            modality=input_modality,
+            classes=class_names,
+            test_mode=False,
+            # 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',
+            # load one frame every five frames
+            load_interval=5)),
+    val=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file=data_root + 'waymo_infos_val.pkl',
+        split='training',
+        pipeline=test_pipeline,
+        modality=input_modality,
+        classes=class_names,
+        test_mode=True,
+        box_type_3d='LiDAR'),
+    test=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file=data_root + 'waymo_infos_val.pkl',
+        split='training',
+        pipeline=test_pipeline,
+        modality=input_modality,
+        classes=class_names,
+        test_mode=True,
+        box_type_3d='LiDAR'))
+
+evaluation = dict(interval=24, pipeline=test_pipeline)