| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172 |
- _base_ = [
- '../_base_/datasets/coco_detection.py',
- '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
- ]
- model = dict(
- type='ATSS',
- 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,
- start_level=1,
- add_extra_convs='on_output',
- num_outs=5),
- dict(type='DyHead', in_channels=256, out_channels=256, num_blocks=6)
- ],
- bbox_head=dict(
- type='ATSSHead',
- num_classes=80,
- in_channels=256,
- stacked_convs=0,
- feat_channels=256,
- anchor_generator=dict(
- type='AnchorGenerator',
- ratios=[1.0],
- octave_base_scale=8,
- scales_per_octave=1,
- strides=[8, 16, 32, 64, 128]),
- bbox_coder=dict(
- type='DeltaXYWHBBoxCoder',
- target_means=[.0, .0, .0, .0],
- target_stds=[0.1, 0.1, 0.2, 0.2]),
- loss_cls=dict(
- type='FocalLoss',
- use_sigmoid=True,
- gamma=2.0,
- alpha=0.25,
- loss_weight=1.0),
- loss_bbox=dict(type='GIoULoss', loss_weight=2.0),
- loss_centerness=dict(
- type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)),
- # training and testing settings
- train_cfg=dict(
- assigner=dict(type='ATSSAssigner', topk=9),
- allowed_border=-1,
- pos_weight=-1,
- debug=False),
- test_cfg=dict(
- nms_pre=1000,
- min_bbox_size=0,
- score_thr=0.05,
- nms=dict(type='nms', iou_threshold=0.6),
- max_per_img=100))
- # optimizer
- optim_wrapper = dict(optimizer=dict(lr=0.01))
|
