-
Notifications
You must be signed in to change notification settings - Fork 3
/
db_r18_mlt2017.yaml
159 lines (148 loc) · 4.21 KB
/
db_r18_mlt2017.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
system:
mode: 0 # 0 for graph mode, 1 for pynative mode in MindSpore
distribute: True
amp_level: 'O0'
seed: 42
log_interval: 10
val_while_train: True
drop_overflow_update: False
model:
type: det
transform: null
backbone:
name: det_resnet18
pretrained: False
neck:
name: DBFPN
out_channels: 256
bias: False
head:
name: DBHead
k: 50
bias: False
adaptive: True
pretrained: https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_resnet18_synthtext-251ef3dd.ckpt
postprocess:
name: DBPostprocess
box_type: quad # whether to output a polygon or a box
binary_thresh: 0.3 # binarization threshold
box_thresh: 0.6 # box score threshold
max_candidates: 1000
expand_ratio: 1.5 # coefficient for expanding predictions
metric:
name: DetMetric
main_indicator: f-score
loss:
name: DBLoss
eps: 1.0e-6
l1_scale: 10
bce_scale: 5
bce_replace: bceloss
scheduler:
scheduler: polynomial_decay
lr: 0.056
num_epochs: 1200
decay_rate: 0.9
warmup_epochs: 3
optimizer:
opt: SGD
filter_bias_and_bn: false
momentum: 0.9
weight_decay: 1.0e-4
# only used for mixed precision training
loss_scaler:
type: dynamic
loss_scale: 512
scale_factor: 2
scale_window: 1000
train:
ckpt_save_dir: './tmp_det'
dataset_sink_mode: True
dataset:
type: DetDataset
dataset_root: /data/ocr_datasets
data_dir: MLT_2017/train
label_file: MLT_2017/train_det_gt.txt
sample_ratio: 1.0
transform_pipeline:
- DecodeImage:
img_mode: RGB
to_float32: False
- DetLabelEncode:
- RandomScale:
scale_range: [ 0.5, 3.0 ]
p: 1.0
- RandomCropWithBBox:
max_tries: 10
min_crop_ratio: 0.1
crop_size: [ 640, 640 ]
p: 1.0
- RandomColorAdjust:
brightness: 0.1255 # 32.0 / 255
saturation: 0.5
- RandomHorizontalFlip:
p: 0.5
- RandomRotate:
degrees: [ -10, 10 ]
expand_canvas: False
p: 1.0
- ValidatePolygons:
- ShrinkBinaryMap:
min_text_size: 8
shrink_ratio: 0.4
- BorderMap:
shrink_ratio: 0.4
thresh_min: 0.3
thresh_max: 0.7
- NormalizeImage:
bgr_to_rgb: False
is_hwc: True
mean: imagenet
std: imagenet
- ToCHWImage:
# the order of the dataloader list, matching the network input and the input labels for the loss function, and optional data for debug/visualize
output_columns: [ 'image', 'binary_map', 'mask', 'thresh_map', 'thresh_mask' ] #'img_path']
# output_columns: ['image'] # for debug op performance
net_input_column_index: [0] # input indices for network forward func in output_columns
label_column_index: [1, 2, 3, 4] # input indices marked as label
loader:
shuffle: True
batch_size: 20
drop_remainder: True
num_workers: 8
eval:
ckpt_load_path: tmp_det/best.ckpt
dataset_sink_mode: False
dataset:
type: DetDataset
dataset_root: /data/ocr_datasets
data_dir: MLT_2017/validation
label_file: MLT_2017/validation_det_gt.txt
sample_ratio: 1.0
transform_pipeline:
- DecodeImage:
img_mode: RGB
to_float32: False
# img_144.jpg, img_150.jpg, img_153.jpg ~ img_161.jpg, img_169.jpg, img_173.jpg, img_174.jpg, img_176.jpg
# have not matching orientation with the gt labels
ignore_orientation: True
- DetLabelEncode:
- DetResize:
target_size: [ 1152, 2048 ] # h, w
keep_ratio: True
padding: True
- NormalizeImage:
bgr_to_rgb: False
is_hwc: True
mean: imagenet
std: imagenet
- ToCHWImage:
# the order of the dataloader list, matching the network input and the labels for evaluation
output_columns: [ 'image', 'polys', 'ignore_tags', 'shape_list' ]
net_input_column_index: [0] # input indices for network forward func in output_columns
label_column_index: [1, 2] # input indices marked as label
loader:
shuffle: False
batch_size: 1 # TODO: due to dynamic shape of polygons (num of boxes varies), BS has to be 1
drop_remainder: False
num_workers: 2