-
Notifications
You must be signed in to change notification settings - Fork 26
/
atss_x101_dcn_fpn_relation_coco_2x.py
242 lines (242 loc) · 8.25 KB
/
atss_x101_dcn_fpn_relation_coco_2x.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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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', file_client_args=dict(backend='zip')),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Resize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
dict(type='LoadImageFromFile', file_client_args=dict(backend='zip')),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='CocoDataset',
ann_file='data/coco/annotations/instances_train2017.json',
img_prefix='data/coco/train2017/',
pipeline=[
dict(
type='LoadImageFromFile',
file_client_args=dict(backend='zip')),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Resize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]),
val=dict(
type='CocoDataset',
ann_file='data/coco/annotations/instances_val2017.json',
img_prefix='data/coco/val2017/',
pipeline=[
dict(
type='LoadImageFromFile',
file_client_args=dict(backend='zip')),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='CocoDataset',
ann_file='data/coco/annotations/instances_val2017.json',
img_prefix='data/coco/val2017/',
pipeline=[
dict(
type='LoadImageFromFile',
file_client_args=dict(backend='zip')),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]))
evaluation = dict(interval=1, metric='bbox')
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[16, 19])
total_epochs = 20
checkpoint_config = dict(interval=1, create_symlink=False)
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
dict(
type='GlobalWandbLoggerHook',
init_kwargs=dict(project='keypoint', entity='det'))
])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = 'work_dirs/bvr_atss_x101_dcn_fpn_2x_coco/epoch_3.pth'
workflow = [('train', 1)]
model = dict(
type='BVR',
pretrained='open-mmlab://resnext101_64x4d',
backbone=dict(
type='ResNeXt',
depth=101,
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',
groups=64,
base_width=4,
dcn=dict(type='DCNv2', deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True),
with_cp=True),
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='BVRHead',
bbox_head_cfg=dict(
type='ATSSHead',
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, 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),
dcn_on_last_conv=True),
keypoint_pos='input',
keypoint_head_cfg=dict(
type='KeypointHead',
num_classes=80,
in_channels=256,
stacked_convs=2,
strides=[8, 16, 32, 64, 128],
shared_stacked_convs=0,
logits_convs=1,
head_types=['top_left_corner', 'bottom_right_corner', 'center'],
corner_pooling=False,
loss_offset=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0),
loss_cls=dict(type='GaussianFocalLoss', loss_weight=0.25)),
cls_keypoint_cfg=dict(
keypoint_types=['center'],
with_key_score=False,
with_relation=True),
reg_keypoint_cfg=dict(
keypoint_types=['top_left_corner', 'bottom_right_corner'],
with_key_score=False,
with_relation=True),
keypoint_cfg=dict(max_keypoint_num=20, keypoint_score_thr=0.0),
feature_selection_cfg=dict(
selection_method='index',
cross_level_topk=50,
cross_level_selection=True),
num_attn_heads=8,
scale_position=False,
pos_cfg=dict(base_size=[300, 300], log_scale=True),
shared_positional_encoding_outer=True))
train_cfg = dict(
bbox=dict(
assigner=dict(type='ATSSAssigner', topk=9),
allowed_border=-1,
pos_weight=-1,
debug=False),
keypoint=dict(
assigner=dict(type='PointKptAssigner'),
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)
gpu_ids = range(0, 8)