|
_base_ = [ |
|
'../_base_/datasets/coco_detection.py', |
|
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' |
|
] |
|
|
|
model = dict( |
|
type='DDOD', |
|
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), |
|
bbox_head=dict( |
|
type='DDODHead', |
|
num_classes=80, |
|
in_channels=256, |
|
stacked_convs=4, |
|
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_iou=dict( |
|
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)), |
|
train_cfg=dict( |
|
|
|
assigner=dict(type='ATSSAssigner', topk=9, alpha=0.8), |
|
reg_assigner=dict(type='ATSSAssigner', topk=9, alpha=0.5), |
|
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)) |
|
|
|
|
|
data = dict(persistent_workers=True) |
|
|
|
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001) |
|
|
