12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364 |
- # model settings
- model = dict(
- type='RPN',
- data_preprocessor=dict(
- type='DetDataPreprocessor',
- mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375],
- bgr_to_rgb=True,
- pad_size_divisor=32),
- backbone=dict(
- type='ResNet',
- depth=50,
- num_stages=4,
- out_indices=(0, 1, 2, 3),
- frozen_stages=1,
- norm_cfg=dict(type='BN', requires_grad=True),
- norm_eval=True,
- style='pytorch',
- init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
- neck=dict(
- type='FPN',
- in_channels=[256, 512, 1024, 2048],
- out_channels=256,
- num_outs=5),
- rpn_head=dict(
- type='RPNHead',
- in_channels=256,
- feat_channels=256,
- anchor_generator=dict(
- type='AnchorGenerator',
- scales=[8],
- ratios=[0.5, 1.0, 2.0],
- strides=[4, 8, 16, 32, 64]),
- bbox_coder=dict(
- type='DeltaXYWHBBoxCoder',
- target_means=[.0, .0, .0, .0],
- target_stds=[1.0, 1.0, 1.0, 1.0]),
- loss_cls=dict(
- type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
- loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
- # model training and testing settings
- train_cfg=dict(
- rpn=dict(
- assigner=dict(
- type='MaxIoUAssigner',
- pos_iou_thr=0.7,
- neg_iou_thr=0.3,
- min_pos_iou=0.3,
- ignore_iof_thr=-1),
- sampler=dict(
- type='RandomSampler',
- num=256,
- pos_fraction=0.5,
- neg_pos_ub=-1,
- add_gt_as_proposals=False),
- allowed_border=-1,
- pos_weight=-1,
- debug=False)),
- test_cfg=dict(
- rpn=dict(
- nms_pre=2000,
- max_per_img=1000,
- nms=dict(type='nms', iou_threshold=0.7),
- min_bbox_size=0)))
|