|
- _base_ = '../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py'
- norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
- model = dict(
- pretrained='open-mmlab://detectron/resnet50_gn',
- backbone=dict(norm_cfg=norm_cfg),
- neck=dict(norm_cfg=norm_cfg),
- roi_head=dict(
- bbox_head=dict(
- type='Shared4Conv1FCBBoxHead',
- conv_out_channels=256,
- norm_cfg=norm_cfg),
- mask_head=dict(norm_cfg=norm_cfg)))
- img_norm_cfg = dict(
- mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
- train_pipeline = [
- dict(type='LoadImageFromFile'),
- dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
- dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
- dict(type='RandomFlip', flip_ratio=0.5),
- 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']),
- ]
- test_pipeline = [
- dict(type='LoadImageFromFile'),
- dict(
- type='MultiScaleFlipAug',
- img_scale=(1333, 800),
- flip=False,
- transforms=[
- dict(type='Resize', keep_ratio=True),
- dict(type='RandomFlip'),
- dict(type='Normalize', **img_norm_cfg),
- dict(type='Pad', size_divisor=32),
- dict(type='ImageToTensor', keys=['img']),
- dict(type='Collect', keys=['img']),
- ])
- ]
- data = dict(
- train=dict(pipeline=train_pipeline),
- val=dict(pipeline=test_pipeline),
- test=dict(pipeline=test_pipeline))
- # learning policy
- lr_config = dict(step=[16, 22])
- total_epochs = 24
|