-
Notifications
You must be signed in to change notification settings - Fork 1.2k
/
res50_coco_512x512.py
159 lines (152 loc) · 4.32 KB
/
res50_coco_512x512.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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
_base_ = [
'../../../../_base_/default_runtime.py',
'../../../../_base_/datasets/coco.py'
]
checkpoint_config = dict(interval=50)
evaluation = dict(interval=50, metric='mAP', save_best='AP')
optimizer = dict(
type='Adam',
lr=0.0015,
)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[200, 260])
total_epochs = 300
channel_cfg = dict(
dataset_joints=17,
dataset_channel=[
[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16],
],
inference_channel=[
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16
])
data_cfg = dict(
image_size=512,
base_size=256,
base_sigma=2,
heatmap_size=[128],
num_joints=channel_cfg['dataset_joints'],
dataset_channel=channel_cfg['dataset_channel'],
inference_channel=channel_cfg['inference_channel'],
num_scales=1,
scale_aware_sigma=False,
)
# model settings
model = dict(
type='AssociativeEmbedding',
pretrained='torchvision://resnet50',
backbone=dict(type='ResNet', depth=50),
keypoint_head=dict(
type='AESimpleHead',
in_channels=2048,
num_joints=17,
tag_per_joint=True,
with_ae_loss=[True],
loss_keypoint=dict(
type='MultiLossFactory',
num_joints=17,
num_stages=1,
ae_loss_type='exp',
with_ae_loss=[True],
push_loss_factor=[0.001],
pull_loss_factor=[0.001],
with_heatmaps_loss=[True],
heatmaps_loss_factor=[1.0],
)),
train_cfg=dict(),
test_cfg=dict(
num_joints=channel_cfg['dataset_joints'],
max_num_people=30,
scale_factor=[1],
with_heatmaps=[True],
with_ae=[True],
project2image=True,
align_corners=False,
nms_kernel=5,
nms_padding=2,
tag_per_joint=True,
detection_threshold=0.1,
tag_threshold=1,
use_detection_val=True,
ignore_too_much=False,
adjust=True,
refine=True,
flip_test=True))
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='BottomUpRandomAffine',
rot_factor=30,
scale_factor=[0.75, 1.5],
scale_type='short',
trans_factor=40),
dict(type='BottomUpRandomFlip', flip_prob=0.5),
dict(type='ToTensor'),
dict(
type='NormalizeTensor',
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]),
dict(
type='BottomUpGenerateTarget',
sigma=2,
max_num_people=30,
),
dict(
type='Collect',
keys=['img', 'joints', 'targets', 'masks'],
meta_keys=[]),
]
val_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='BottomUpGetImgSize', test_scale_factor=[1]),
dict(
type='BottomUpResizeAlign',
transforms=[
dict(type='ToTensor'),
dict(
type='NormalizeTensor',
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]),
]),
dict(
type='Collect',
keys=['img'],
meta_keys=[
'image_file', 'aug_data', 'test_scale_factor', 'base_size',
'center', 'scale', 'flip_index'
]),
]
test_pipeline = val_pipeline
data_root = 'data/coco'
data = dict(
workers_per_gpu=1,
train_dataloader=dict(samples_per_gpu=24),
val_dataloader=dict(samples_per_gpu=1),
test_dataloader=dict(samples_per_gpu=1),
train=dict(
type='BottomUpCocoDataset',
ann_file=f'{data_root}/annotations/person_keypoints_train2017.json',
img_prefix=f'{data_root}/train2017/',
data_cfg=data_cfg,
pipeline=train_pipeline,
dataset_info={{_base_.dataset_info}}),
val=dict(
type='BottomUpCocoDataset',
ann_file=f'{data_root}/annotations/person_keypoints_val2017.json',
img_prefix=f'{data_root}/val2017/',
data_cfg=data_cfg,
pipeline=val_pipeline,
dataset_info={{_base_.dataset_info}}),
test=dict(
type='BottomUpCocoDataset',
ann_file=f'{data_root}/annotations/person_keypoints_val2017.json',
img_prefix=f'{data_root}/val2017/',
data_cfg=data_cfg,
pipeline=test_pipeline,
dataset_info={{_base_.dataset_info}}),
)