forked from PaddlePaddle/PaddleDetection
-
Notifications
You must be signed in to change notification settings - Fork 2
/
cascade_rcnn_r50_fpn_1x_ms_test.yml
161 lines (147 loc) · 2.99 KB
/
cascade_rcnn_r50_fpn_1x_ms_test.yml
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
architecture: CascadeRCNN
max_iters: 90000
snapshot_iter: 10000
use_gpu: true
log_iter: 20
save_dir: output
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
weights: output/cascade_rcnn_r50_fpn_1x/model_final
metric: COCO
num_classes: 81
CascadeRCNN:
backbone: ResNet
fpn: FPN
rpn_head: FPNRPNHead
roi_extractor: FPNRoIAlign
bbox_head: CascadeBBoxHead
bbox_assigner: CascadeBBoxAssigner
ResNet:
norm_type: affine_channel
depth: 50
feature_maps: [2, 3, 4, 5]
freeze_at: 2
variant: b
FPN:
min_level: 2
max_level: 6
num_chan: 256
spatial_scale: [0.03125, 0.0625, 0.125, 0.25]
FPNRPNHead:
anchor_generator:
anchor_sizes: [32, 64, 128, 256, 512]
aspect_ratios: [0.5, 1.0, 2.0]
stride: [16.0, 16.0]
variance: [1.0, 1.0, 1.0, 1.0]
anchor_start_size: 32
min_level: 2
max_level: 6
num_chan: 256
rpn_target_assign:
rpn_batch_size_per_im: 256
rpn_fg_fraction: 0.5
rpn_positive_overlap: 0.7
rpn_negative_overlap: 0.3
rpn_straddle_thresh: 0.0
train_proposal:
min_size: 0.0
nms_thresh: 0.7
pre_nms_top_n: 2000
post_nms_top_n: 2000
test_proposal:
min_size: 0.0
nms_thresh: 0.7
pre_nms_top_n: 1000
post_nms_top_n: 1000
FPNRoIAlign:
canconical_level: 4
canonical_size: 224
min_level: 2
max_level: 5
box_resolution: 7
sampling_ratio: 2
CascadeBBoxAssigner:
batch_size_per_im: 512
bbox_reg_weights: [10, 20, 30]
bg_thresh_lo: [0.0, 0.0, 0.0]
bg_thresh_hi: [0.5, 0.6, 0.7]
fg_thresh: [0.5, 0.6, 0.7]
fg_fraction: 0.25
CascadeBBoxHead:
head: CascadeTwoFCHead
nms:
keep_top_k: 100
nms_threshold: 0.5
score_threshold: 0.05
CascadeTwoFCHead:
mlp_dim: 1024
MultiScaleTEST:
score_thresh: 0.05
nms_thresh: 0.5
detections_per_im: 100
enable_voting: true
vote_thresh: 0.9
LearningRate:
base_lr: 0.02
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [60000, 80000]
- !LinearWarmup
start_factor: 0.3333333333333333
steps: 500
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0001
type: L2
_READER_: 'faster_fpn_reader.yml'
TrainReader:
batch_size: 2
EvalReader:
batch_size: 1
inputs_def:
fields: ['image', 'im_info', 'im_id', 'im_shape']
multi_scale: true
num_scales: 18
use_flip: true
dataset:
!COCODataSet
dataset_dir: dataset/coco
anno_path: annotations/instances_val2017.json
image_dir: val2017
sample_transforms:
- !DecodeImage
to_rgb: true
- !NormalizeImage
is_channel_first: false
is_scale: true
mean:
- 0.485
- 0.456
- 0.406
std:
- 0.229
- 0.224
- 0.225
- !MultiscaleTestResize
origin_target_size: 800
origin_max_size: 1333
target_size:
- 400
- 500
- 600
- 700
- 900
- 1000
- 1100
- 1200
max_size: 2000
use_flip: true
- !Permute
channel_first: true
to_bgr: false
- !PadMultiScaleTest
pad_to_stride: 32
worker_num: 2