-
Notifications
You must be signed in to change notification settings - Fork 9.3k
/
sabl_retinanet_r101_fpn_gn_2x_ms_480_960_coco.py
73 lines (73 loc) · 2.42 KB
/
sabl_retinanet_r101_fpn_gn_2x_ms_480_960_coco.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
_base_ = [
'../_base_/models/retinanet_r50_fpn.py',
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_2x.py', '../_base_/default_runtime.py'
]
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
backbone=dict(
depth=101,
init_cfg=dict(type='Pretrained',
checkpoint='torchvision://resnet101')),
bbox_head=dict(
_delete_=True,
type='SABLRetinaHead',
num_classes=80,
in_channels=256,
stacked_convs=4,
feat_channels=256,
approx_anchor_generator=dict(
type='AnchorGenerator',
octave_base_scale=4,
scales_per_octave=3,
ratios=[0.5, 1.0, 2.0],
strides=[8, 16, 32, 64, 128]),
square_anchor_generator=dict(
type='AnchorGenerator',
ratios=[1.0],
scales=[4],
strides=[8, 16, 32, 64, 128]),
norm_cfg=norm_cfg,
bbox_coder=dict(
type='BucketingBBoxCoder', num_buckets=14, scale_factor=3.0),
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.5),
loss_bbox_reg=dict(
type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.5)),
# training and testing settings
train_cfg=dict(
assigner=dict(
type='ApproxMaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0.0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Resize',
img_scale=[(1333, 480), (1333, 960)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
data = dict(train=dict(pipeline=train_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)