| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263 |
- # model settings
- input_size = 300
- model = dict(
- type='SingleStageDetector',
- data_preprocessor=dict(
- type='DetDataPreprocessor',
- mean=[123.675, 116.28, 103.53],
- std=[1, 1, 1],
- bgr_to_rgb=True,
- pad_size_divisor=1),
- backbone=dict(
- type='SSDVGG',
- depth=16,
- with_last_pool=False,
- ceil_mode=True,
- out_indices=(3, 4),
- out_feature_indices=(22, 34),
- init_cfg=dict(
- type='Pretrained', checkpoint='open-mmlab://vgg16_caffe')),
- neck=dict(
- type='SSDNeck',
- in_channels=(512, 1024),
- out_channels=(512, 1024, 512, 256, 256, 256),
- level_strides=(2, 2, 1, 1),
- level_paddings=(1, 1, 0, 0),
- l2_norm_scale=20),
- bbox_head=dict(
- type='SSDHead',
- in_channels=(512, 1024, 512, 256, 256, 256),
- num_classes=80,
- anchor_generator=dict(
- type='SSDAnchorGenerator',
- scale_major=False,
- input_size=input_size,
- basesize_ratio_range=(0.15, 0.9),
- strides=[8, 16, 32, 64, 100, 300],
- ratios=[[2], [2, 3], [2, 3], [2, 3], [2], [2]]),
- bbox_coder=dict(
- type='DeltaXYWHBBoxCoder',
- target_means=[.0, .0, .0, .0],
- target_stds=[0.1, 0.1, 0.2, 0.2])),
- # model training and testing settings
- train_cfg=dict(
- assigner=dict(
- type='MaxIoUAssigner',
- pos_iou_thr=0.5,
- neg_iou_thr=0.5,
- min_pos_iou=0.,
- ignore_iof_thr=-1,
- gt_max_assign_all=False),
- sampler=dict(type='PseudoSampler'),
- smoothl1_beta=1.,
- allowed_border=-1,
- pos_weight=-1,
- neg_pos_ratio=3,
- debug=False),
- test_cfg=dict(
- nms_pre=1000,
- nms=dict(type='nms', iou_threshold=0.45),
- min_bbox_size=0,
- score_thr=0.02,
- max_per_img=200))
- cudnn_benchmark = True
|
