-
Notifications
You must be signed in to change notification settings - Fork 17
/
maet_yolo_ug2.py
129 lines (125 loc) · 4.08 KB
/
maet_yolo_ug2.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
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
_base_ = '../_base_/default_runtime.py'
load_from = '/home/czt/mmdetection_v1/work_dirs/maet_yolo_coco_ort/latest.pth'
# model settings
model = dict(
type='YOLOV3',
pretrained='open-mmlab://darknet53',
backbone=dict(type='Darknet', depth=53, out_indices=(3, 4, 5)),
neck=dict(
type='YOLOV3Neck',
num_scales=3,
in_channels=[1024, 512, 256],
out_channels=[512, 256, 128]),
bbox_head=dict(
type='YOLOV3Head',
num_classes=1,
in_channels=[512, 256, 128],
out_channels=[1024, 512, 256],
anchor_generator=dict(
type='YOLOAnchorGenerator',
base_sizes=[[(58, 45), (78, 99), (180, 163)],
[(15, 31), (32, 25), (29, 59)],
[(5, 8), (8, 15), (23, 13)]],
strides=[32, 16, 8]),
bbox_coder=dict(type='YOLOBBoxCoder'),
featmap_strides=[32, 16, 8],
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=True,
loss_weight=1.0,
reduction='sum'),
loss_conf=dict(
type='CrossEntropyLoss',
use_sigmoid=True,
loss_weight=1.0,
reduction='sum'),
loss_xy=dict(
type='CrossEntropyLoss',
use_sigmoid=True,
loss_weight=2.0,
reduction='sum'),
loss_wh=dict(type='MSELoss', loss_weight=2.0, reduction='sum')))
# training and testing settings
train_cfg = dict(
assigner=dict(
type='GridAssigner', pos_iou_thr=0.5, neg_iou_thr=0.5, min_pos_iou=0))
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
conf_thr=0.005,
nms=dict(type='nms', iou_thr=0.55),
max_per_img=100)
# dataset settings
dataset_type = 'UG2FaceDataset'
data_root = '/home/czt/DataSets/Dark_face_2019/'
img_norm_cfg = dict(mean=[0, 0, 0], std=[255., 255., 255.], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile', to_float32=True),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Expand',
mean=img_norm_cfg['mean'],
to_rgb=img_norm_cfg['to_rgb'],
ratio_range=(1, 2)),
dict(
type='MinIoURandomCrop',
min_ious=(0.4, 0.5, 0.6, 0.7, 0.8, 0.9),
min_crop_size=0.3),
dict(type='Resize', img_scale=[(320, 320), (608, 608)], keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg), #this step change the images from bgr2rgb
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
#return img gt_bboxer gt_labels
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(664, 664),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=12,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=3,
dataset=dict(
type=dataset_type,
ann_file = data_root + 'main/train.txt',
img_prefix=data_root,
pipeline=train_pipeline)),
val=dict(
type=dataset_type,
ann_file = data_root + 'main/val.txt',
img_prefix=data_root,
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file = data_root + 'main/val.txt',
img_prefix=data_root,
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0005)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
#warmup='linear',
#warmup_iters=2000, # same as burn-in in darknet
#warmup_ratio=0.1,
step=[14, 18])
# runtime settings
total_epochs = 20
evaluation = dict(interval=1, metric=['mAP'])