object_detection/configs/convnext/cascade_mask_rcnn_convnext_base_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco_in22k.py [86:131]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)

# augmentation strategy originates from DETR / Sparse RCNN
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(type='AutoAugment',
         policies=[
             [
                 dict(type='Resize',
                      img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
                                 (608, 1333), (640, 1333), (672, 1333), (704, 1333),
                                 (736, 1333), (768, 1333), (800, 1333)],
                      multiscale_mode='value',
                      keep_ratio=True)
             ],
             [
                 dict(type='Resize',
                      img_scale=[(400, 1333), (500, 1333), (600, 1333)],
                      multiscale_mode='value',
                      keep_ratio=True),
                 dict(type='RandomCrop',
                      crop_type='absolute_range',
                      crop_size=(384, 600),
                      allow_negative_crop=True),
                 dict(type='Resize',
                      img_scale=[(480, 1333), (512, 1333), (544, 1333),
                                 (576, 1333), (608, 1333), (640, 1333),
                                 (672, 1333), (704, 1333), (736, 1333),
                                 (768, 1333), (800, 1333)],
                      multiscale_mode='value',
                      override=True,
                      keep_ratio=True)
             ]
         ]),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
data = dict(train=dict(pipeline=train_pipeline))

optimizer = dict(constructor='LearningRateDecayOptimizerConstructor', _delete_=True, type='AdamW', 
                 lr=0.0001, betas=(0.9, 0.999), weight_decay=0.05,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



object_detection/configs/convnext/mask_rcnn_convnext_tiny_patch4_window7_mstrain_480-800_adamw_3x_coco_in1k.py [26:71]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)

# augmentation strategy originates from DETR / Sparse RCNN
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(type='AutoAugment',
         policies=[
             [
                 dict(type='Resize',
                      img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
                                 (608, 1333), (640, 1333), (672, 1333), (704, 1333),
                                 (736, 1333), (768, 1333), (800, 1333)],
                      multiscale_mode='value',
                      keep_ratio=True)
             ],
             [
                 dict(type='Resize',
                      img_scale=[(400, 1333), (500, 1333), (600, 1333)],
                      multiscale_mode='value',
                      keep_ratio=True),
                 dict(type='RandomCrop',
                      crop_type='absolute_range',
                      crop_size=(384, 600),
                      allow_negative_crop=True),
                 dict(type='Resize',
                      img_scale=[(480, 1333), (512, 1333), (544, 1333),
                                 (576, 1333), (608, 1333), (640, 1333),
                                 (672, 1333), (704, 1333), (736, 1333),
                                 (768, 1333), (800, 1333)],
                      multiscale_mode='value',
                      override=True,
                      keep_ratio=True)
             ]
         ]),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
data = dict(train=dict(pipeline=train_pipeline))

optimizer = dict(constructor='LearningRateDecayOptimizerConstructor', _delete_=True, type='AdamW', 
                 lr=0.0001, betas=(0.9, 0.999), weight_decay=0.05,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -