_base_ = [
    '_base_dbnet_resnet18_fpnc.py',
    '../_base_/datasets/totaltext.py',
    '../_base_/default_runtime.py',
    '../_base_/schedules/schedule_sgd_1200e.py',
]

train_pipeline = [
    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
    dict(
        type='LoadOCRAnnotations',
        with_polygon=True,
        with_bbox=True,
        with_label=True,
    ),
    dict(type='FixInvalidPolygon', min_poly_points=4),
    dict(
        type='TorchVisionWrapper',
        op='ColorJitter',
        brightness=32.0 / 255,
        saturation=0.5),
    dict(
        type='ImgAugWrapper',
        args=[['Fliplr', 0.5],
              dict(cls='Affine', rotate=[-10, 10]), ['Resize', [0.5, 3.0]]]),
    dict(type='RandomCrop', min_side_ratio=0.1),
    dict(type='Resize', scale=(640, 640), keep_ratio=True),
    dict(type='Pad', size=(640, 640)),
    dict(
        type='PackTextDetInputs',
        meta_keys=('img_path', 'ori_shape', 'img_shape'))
]

test_pipeline = [
    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
    dict(type='Resize', scale=(1333, 736), keep_ratio=True),
    dict(
        type='LoadOCRAnnotations',
        with_polygon=True,
        with_bbox=True,
        with_label=True,
    ),
    dict(type='FixInvalidPolygon', min_poly_points=4),
    dict(
        type='PackTextDetInputs',
        meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor'))
]

# dataset settings
totaltext_textdet_train = _base_.totaltext_textdet_train
totaltext_textdet_test = _base_.totaltext_textdet_test
totaltext_textdet_train.pipeline = train_pipeline
totaltext_textdet_test.pipeline = test_pipeline

train_dataloader = dict(
    batch_size=16,
    num_workers=16,
    pin_memory=True,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    dataset=totaltext_textdet_train)

val_dataloader = dict(
    batch_size=1,
    num_workers=1,
    pin_memory=True,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=totaltext_textdet_test)

test_dataloader = val_dataloader

auto_scale_lr = dict(base_batch_size=16)