_base_ = '../mask_rcnn/mask-rcnn_r50_fpn_1x_coco.py'

albu_train_transforms = [
    dict(
        type='ShiftScaleRotate',
        shift_limit=0.0625,
        scale_limit=0.0,
        rotate_limit=0,
        interpolation=1,
        p=0.5),
    dict(
        type='RandomBrightnessContrast',
        brightness_limit=[0.1, 0.3],
        contrast_limit=[0.1, 0.3],
        p=0.2),
    dict(
        type='OneOf',
        transforms=[
            dict(
                type='RGBShift',
                r_shift_limit=10,
                g_shift_limit=10,
                b_shift_limit=10,
                p=1.0),
            dict(
                type='HueSaturationValue',
                hue_shift_limit=20,
                sat_shift_limit=30,
                val_shift_limit=20,
                p=1.0)
        ],
        p=0.1),
    dict(type='JpegCompression', quality_lower=85, quality_upper=95, p=0.2),
    dict(type='ChannelShuffle', p=0.1),
    dict(
        type='OneOf',
        transforms=[
            dict(type='Blur', blur_limit=3, p=1.0),
            dict(type='MedianBlur', blur_limit=3, p=1.0)
        ],
        p=0.1),
]
train_pipeline = [
    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
    dict(
        type='Albu',
        transforms=albu_train_transforms,
        bbox_params=dict(
            type='BboxParams',
            format='pascal_voc',
            label_fields=['gt_bboxes_labels', 'gt_ignore_flags'],
            min_visibility=0.0,
            filter_lost_elements=True),
        keymap={
            'img': 'image',
            'gt_masks': 'masks',
            'gt_bboxes': 'bboxes'
        },
        skip_img_without_anno=True),
    dict(type='RandomFlip', prob=0.5),
    dict(type='PackDetInputs')
]

train_dataloader = dict(dataset=dict(pipeline=train_pipeline))