nus-mono3d.py

dataset_type = 'NuScenesDataset'
data_root = 'data/nuscenes/'
class_names = [
    'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
    'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
metainfo = dict(CLASSES=class_names)
# Input modality for nuScenes dataset, this is consistent with the submission
# format which requires the information in input_modality.
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.
file_client_args = dict(
    backend='petrel',
    path_mapping=dict({
        './data/nuscenes/':
        's3://openmmlab/datasets/detection3d/nuscenes/',
        'data/nuscenes/':
        's3://openmmlab/datasets/detection3d/nuscenes/'
    }))

train_pipeline = [
    dict(type='LoadImageFromFileMono3D', file_client_args=file_client_args),
    dict(
        type='LoadAnnotations3D',
        with_bbox=True,
        with_label=True,
        with_attr_label=True,
        with_bbox_3d=True,
        with_label_3d=True,
        with_bbox_depth=True),
    dict(type='Resize', img_scale=(1600, 900), keep_ratio=True),
    dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
    dict(
        type='Pack3DDetInputs',
        keys=[
            'img', 'gt_bboxes', 'gt_labels', 'attr_labels', 'gt_bboxes_3d',
            'gt_labels_3d', 'centers_2d', 'depths'
        ]),
]

test_pipeline = [
    dict(type='LoadImageFromFileMono3D', file_client_args=file_client_args),
    dict(type='mmdet.Resize', scale=(1600, 900), keep_ratio=True),
    dict(type='Pack3DDetInputs', keys=['img'])
]

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,
        data_prefix=dict(
            pts='',
            CAM_FRONT='samples/CAM_FRONT',
            CAM_FRONT_LEFT='samples/CAM_FRONT_LEFT',
            CAM_FRONT_RIGHT='samples/CAM_FRONT_RIGHT',
            CAM_BACK='samples/CAM_BACK',
            CAM_BACK_RIGHT='samples/CAM_BACK_RIGHT',
            CAM_BACK_LEFT='samples/CAM_BACK_LEFT'),
        ann_file='nuscenes_infos_train.pkl',
        task='mono3d',
        pipeline=train_pipeline,
        metainfo=metainfo,
        modality=input_modality,
        test_mode=False,
        # we use box_type_3d='Camera' in monocular 3d
        # detection task
        box_type_3d='Camera',
        use_valid_flag=True))
val_dataloader = dict(
    batch_size=1,
    num_workers=2,
    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='',
            CAM_FRONT='samples/CAM_FRONT',
            CAM_FRONT_LEFT='samples/CAM_FRONT_LEFT',
            CAM_FRONT_RIGHT='samples/CAM_FRONT_RIGHT',
            CAM_BACK='samples/CAM_BACK',
            CAM_BACK_RIGHT='samples/CAM_BACK_RIGHT',
            CAM_BACK_LEFT='samples/CAM_BACK_LEFT'),
        ann_file='nuscenes_infos_val.pkl',
        task='mono3d',
        pipeline=test_pipeline,
        modality=input_modality,
        metainfo=metainfo,
        test_mode=True,
        box_type_3d='Camera',
        use_valid_flag=True))
test_dataloader = val_dataloader

val_evaluator = dict(
    type='NuScenesMetric',
    data_root=data_root,
    ann_file=data_root + 'nuscenes_infos_val.pkl',
    metric='bbox')

test_evaluator = val_evaluator