| 1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768 |
- # model settings
- model = dict(
- type='FastRCNN',
- 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),
- roi_head=dict(
- type='StandardRoIHead',
- bbox_roi_extractor=dict(
- type='SingleRoIExtractor',
- roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
- out_channels=256,
- featmap_strides=[4, 8, 16, 32]),
- bbox_head=dict(
- type='Shared2FCBBoxHead',
- in_channels=256,
- fc_out_channels=1024,
- roi_feat_size=7,
- num_classes=80,
- bbox_coder=dict(
- type='DeltaXYWHBBoxCoder',
- target_means=[0., 0., 0., 0.],
- target_stds=[0.1, 0.1, 0.2, 0.2]),
- reg_class_agnostic=False,
- loss_cls=dict(
- type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
- loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
- # model training and testing settings
- train_cfg=dict(
- rcnn=dict(
- assigner=dict(
- type='MaxIoUAssigner',
- pos_iou_thr=0.5,
- neg_iou_thr=0.5,
- min_pos_iou=0.5,
- match_low_quality=False,
- ignore_iof_thr=-1),
- sampler=dict(
- type='RandomSampler',
- num=512,
- pos_fraction=0.25,
- neg_pos_ub=-1,
- add_gt_as_proposals=True),
- pos_weight=-1,
- debug=False)),
- test_cfg=dict(
- rcnn=dict(
- score_thr=0.05,
- nms=dict(type='nms', iou_threshold=0.5),
- max_per_img=100)))
|
