-
Notifications
You must be signed in to change notification settings - Fork 65
/
pascal_voc.yaml
191 lines (178 loc) · 3.21 KB
/
pascal_voc.yaml
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
---
MXNET_VERSION: "mxnet"
output_path: "./output/retinanet/"
symbol: retina_resnet_50
gpus: '0'
CLASS_AGNOSTIC: false
SCALES:
- 896
- 1408
default:
frequent: 100
kvstore: device
network:
pretrained: "./model/pretrained_model/resnet-50"
pretrained_epoch: 0
PIXEL_MEANS:
- 103.06
- 115.90
- 123.15
IMAGE_STRIDE: 128
FIXED_PARAMS:
FIXED_PARAMS_SHARED:
- conv1
- bn_conv1
- res2
- bn2
- res3
- bn3
- res4
- bn4
- gamma
- beta
p4_RCNN_FEAT_STRIDE: 16
p4_RPN_FEAT_STRIDE: 16
p4_ANCHOR_RATIOS:
- 0.5
- 1
- 2
p4_ANCHOR_SCALES:
- 8
- 10
- 12
p4_NUM_ANCHORS: 9
p5_RCNN_FEAT_STRIDE: 32
p5_RPN_FEAT_STRIDE: 32
p5_ANCHOR_RATIOS:
- 0.5
- 1
- 2
p5_ANCHOR_SCALES:
- 8
- 10
- 12
p5_NUM_ANCHORS: 9
p6_RCNN_FEAT_STRIDE: 64
p6_RPN_FEAT_STRIDE: 64
p6_ANCHOR_RATIOS:
- 0.5
- 1
- 2
p6_ANCHOR_SCALES:
- 8
- 10
- 12
p6_NUM_ANCHORS: 9
p7_RCNN_FEAT_STRIDE: 128
p7_RPN_FEAT_STRIDE: 128
p7_ANCHOR_RATIOS:
- 0.5
- 1
- 2
p7_ANCHOR_SCALES:
- 8
- 10
- 12
p7_NUM_ANCHORS: 9
dataset:
NUM_CLASSES: 21
dataset: PascalVOC
dataset_path: "./data/voc/VOCdevkit2007"
image_set: 2007_trainval
root_path: "./data"
test_image_set: 2007_test
proposal: rpn
TRAIN:
lr: 0.00001
lr_step: '100000.333'
warmup: false
warmup_lr: 0.0002
# typically we will use 8000 warmup step for single GPU for COCO
warmup_step: 1000
begin_epoch: 0
end_epoch: 1000
model_prefix: 'rcnn_kitti'
# whether resume training
RESUME: false
# whether flip image
FLIP: true
# whether shuffle image
SHUFFLE: false
# whether use OHEM
ENABLE_OHEM: false
# size of images for each device, 2 for rcnn, 1 for rpn and e2e
BATCH_IMAGES: 1
# e2e changes behavior of anchor loader and metric
END2END: true
# group images with similar aspect ratio
ASPECT_GROUPING: true
# R-CNN
# rcnn rois batch size
BATCH_ROIS: 128
BATCH_ROIS_OHEM: 128
# rcnn rois sampling params
FG_FRACTION: 0.25
FG_THRESH: 0.5
BG_THRESH_HI: 0.5
BG_THRESH_LO: 0.1
# rcnn bounding box regression params
BBOX_REGRESSION_THRESH: 0.5
BBOX_WEIGHTS:
- 1.0
- 1.0
- 1.0
- 1.0
# RPN anchor loader
# rpn anchors batch size
RPN_BATCH_SIZE: 512
# rpn anchors sampling params
RPN_FG_FRACTION: 0.5
RPN_POSITIVE_OVERLAP: 0.5
RPN_NEGATIVE_OVERLAP: 0.4
RPN_CLOBBER_POSITIVES: false
# rpn bounding box regression params
RPN_BBOX_WEIGHTS:
- 1.0
- 1.0
- 1.0
- 1.0
RPN_POSITIVE_WEIGHT: -1.0
# used for end2end training
# RPN proposal
CXX_PROPOSAL: false
RPN_NMS_THRESH: 0.7
RPN_PRE_NMS_TOP_N: 6000
RPN_POST_NMS_TOP_N: 300
RPN_MIN_SIZE: 0
# approximate bounding box regression
BBOX_NORMALIZATION_PRECOMPUTED: true
BBOX_MEANS:
- 0.0
- 0.0
- 0.0
- 0.0
BBOX_STDS:
- 0.1
- 0.1
- 0.2
- 0.2
TEST:
# use rpn to generate proposal
HAS_RPN: true
# size of images for each device
BATCH_IMAGES: 2
# RPN proposal
CXX_PROPOSAL: false
RPN_NMS_THRESH: 0.7
RPN_PRE_NMS_TOP_N: 6000
RPN_POST_NMS_TOP_N: 300
RPN_MIN_SIZE: 0
# RPN generate proposal
PROPOSAL_NMS_THRESH: 0.7
PROPOSAL_PRE_NMS_TOP_N: 20000
PROPOSAL_POST_NMS_TOP_N: 2000
PROPOSAL_MIN_SIZE: 0
# RCNN nms
NMS: 0.3
test_epoch: 34
max_per_image: 100