mmdetection/configs/_base_/datasets/dsdl.py

dataset_type = 'DSDLDetDataset'
data_root = 'path to dataset folder'
train_ann = 'path to train yaml file'
val_ann = 'path to val yaml file'

backend_args = None
# backend_args = dict(
#     backend='petrel',
#     path_mapping=dict({
#         './data/': "s3://open_data/",
#         'data/': "s3://open_data/"
#     }))

train_pipeline = [
    dict(type='LoadImageFromFile', backend_args=backend_args),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
    dict(type='RandomFlip', prob=0.5),
    dict(type='PackDetInputs')
]
test_pipeline = [
    dict(type='LoadImageFromFile', backend_args=backend_args),
    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
    # If you don't have a gt annotation, delete the pipeline
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='PackDetInputs',
        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
                   'scale_factor', 'instances'))
]

train_dataloader = dict(
    batch_size=2,
    num_workers=2,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    batch_sampler=dict(type='AspectRatioBatchSampler'),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file=train_ann,
        filter_cfg=dict(filter_empty_gt=True, min_size=32, bbox_min_size=32),
        pipeline=train_pipeline))

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,
        ann_file=val_ann,
        test_mode=True,
        pipeline=test_pipeline))

test_dataloader = val_dataloader

val_evaluator = dict(type='CocoMetric', metric='bbox')
# val_evaluator = dict(type='VOCMetric', metric='mAP', eval_mode='11points')
test_evaluator = val_evaluator