|
- _base_ = '../cascade_rcnn/cascade_rcnn_x101_64x4d_fpn_20e_coco.py'
-
- model = dict(
- neck=dict(
- type='FPN_CARAFE',
- in_channels=[256, 512, 1024, 2048],
- out_channels=256,
- num_outs=5,
- start_level=0,
- end_level=-1,
- norm_cfg=None,
- act_cfg=None,
- order=('conv', 'norm', 'act'),
- upsample_cfg=dict(
- type='carafe',
- up_kernel=5,
- up_group=1,
- encoder_kernel=3,
- encoder_dilation=1,
- compressed_channels=64)),
- roi_head=dict(
- bbox_head=[
- dict(
- type='Shared2FCBBoxHead',
- in_channels=256,
- fc_out_channels=1024,
- roi_feat_size=7,
- num_classes=1,
- bbox_coder=dict(
- type='DeltaXYWHBBoxCoder',
- target_means=[0., 0., 0., 0.],
- target_stds=[0.1, 0.1, 0.2, 0.2]),
- reg_class_agnostic=True,
- loss_cls=dict(
- type='FocalLoss',
- use_sigmoid=True,
- gamma=2.0,
- alpha=0.25,
- loss_weight=1.0),
- loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
- loss_weight=1.0)),
- dict(
- type='Shared2FCBBoxHead',
- in_channels=256,
- fc_out_channels=1024,
- roi_feat_size=7,
- num_classes=1,
- bbox_coder=dict(
- type='DeltaXYWHBBoxCoder',
- target_means=[0., 0., 0., 0.],
- target_stds=[0.05, 0.05, 0.1, 0.1]),
- reg_class_agnostic=True,
- loss_cls=dict(
- type='FocalLoss',
- use_sigmoid=True,
- gamma=2.0,
- alpha=0.25,
- loss_weight=1.0),
- loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
- loss_weight=1.0)),
- dict(
- type='Shared2FCBBoxHead',
- in_channels=256,
- fc_out_channels=1024,
- roi_feat_size=7,
- num_classes=1,
- bbox_coder=dict(
- type='DeltaXYWHBBoxCoder',
- target_means=[0., 0., 0., 0.],
- target_stds=[0.033, 0.033, 0.067, 0.067]),
- reg_class_agnostic=True,
- loss_cls=dict(
- type='FocalLoss',
- use_sigmoid=True,
- gamma=2.0,
- alpha=0.25,
- loss_weight=1.0),
- loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
- ]))
-
- dataset_type = 'CocoDataset'
- classes = ('yiwei')
-
- img_norm_cfg = dict(
- mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-
- train_pipeline = [
- dict(type='LoadImageFromFile'),
- dict(type='LoadAnnotations', with_bbox=True),
- dict(
- type='Resize',
- img_scale=[(400, 400), (500, 500)],
- multiscale_mode='value',
- keep_ratio=True),
- dict(type='RandomFlip', flip_ratio=[0.2,0.2,0.2], direction=['horizontal', 'vertical', 'diagonal']),
- dict(type='BrightnessTransform', level=5, prob=0.5),
- dict(type='ContrastTransform', level=5, prob=0.5),
- dict(type='RandomShift', shift_ratio=0.5),
- dict(type='MinIoURandomCrop', min_ious=(0.5, 0.7, 0.9), min_crop_size=0.8),
- dict(type='Normalize', **img_norm_cfg),
- dict(type='Pad', size_divisor=32),
- dict(type='DefaultFormatBundle'),
- dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
- ]
- test_pipeline = [
- dict(type='LoadImageFromFile'),
- dict(
- type='MultiScaleFlipAug',
- img_scale=[(400, 400)],
- 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(
- samples_per_gpu=16,
- workers_per_gpu=8,
- train=dict(
- type=dataset_type,
- img_prefix='/home/shanwei-luo/userdata/datasets/dsxw_dataset_v9_1/dsxw_train/images/',
- classes=classes,
- ann_file='/home/shanwei-luo/userdata/datasets/dsxw_dataset_v9_1/dsxw_train/annotations/train.json',
- pipeline=train_pipeline),
- val=dict(
- type=dataset_type,
- img_prefix='/home/shanwei-luo/userdata/datasets/dsxw_dataset_v9_1/dsxw_test/images/',
- classes=classes,
- ann_file='/home/shanwei-luo/userdata/datasets/dsxw_dataset_v9_1/dsxw_test/annotations/test.json',
- pipeline=test_pipeline),
- test=dict(
- type=dataset_type,
- img_prefix='/home/shanwei-luo/userdata/datasets/dsxw_dataset_v9_1/dsxw_test/images/',
- classes=classes,
- ann_file='/home/shanwei-luo/userdata/datasets/dsxw_dataset_v9_1/dsxw_test/annotations/test.json',
- pipeline=test_pipeline))
-
- # optimizer
- optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
- optimizer_config = dict(grad_clip=None)
- # learning policy
- lr_config = dict(
- policy='CosineAnnealing',
- warmup='linear',
- warmup_iters=1000,
- warmup_ratio=1.0 / 10,
- min_lr_ratio=1e-5)
- runner = dict(type='EpochBasedRunner', max_epochs=60)
-
- evaluation = dict(interval=5, metric='bbox')
|