Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

update multi rec model #6142

Merged
merged 4 commits into from
May 6, 2022
Merged

update multi rec model #6142

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
914b8b8
update multi rec model
tink2123 May 5, 2022
9dd160f
fix pdserving for det
tink2123 May 5, 2022
a771fc6
rename multi config
tink2123 May 5, 2022
5feaaa9
update ch_rec_slim link
tink2123 May 5, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
131 changes: 131 additions & 0 deletions configs/rec/PP-OCRv3/multi_language/arabic_PP-OCRv3_rec.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,131 @@
Global:
debug: false
use_gpu: true
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/v3_arabic_mobile
save_epoch_step: 3
eval_batch_step: [0, 2000]
cal_metric_during_train: true
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: false
infer_img: doc/imgs_words/ch/word_1.jpg
character_dict_path: ppocr/utils/dict/arabic_dict.txt
max_text_length: &max_text_length 25
infer_mode: false
use_space_char: true
distributed: true
save_res_path: ./output/rec/predicts_ppocrv3_arabic.txt


Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
warmup_epoch: 5
regularizer:
name: L2
factor: 3.0e-05


Architecture:
model_type: rec
algorithm: SVTR
Transform:
Backbone:
name: MobileNetV1Enhance
scale: 0.5
last_conv_stride: [1, 2]
last_pool_type: avg
Head:
name: MultiHead
head_list:
- CTCHead:
Neck:
name: svtr
dims: 64
depth: 2
hidden_dims: 120
use_guide: True
Head:
fc_decay: 0.00001
- SARHead:
enc_dim: 512
max_text_length: *max_text_length

Loss:
name: MultiLoss
loss_config_list:
- CTCLoss:
- SARLoss:

PostProcess:
name: CTCLabelDecode

Metric:
name: RecMetric
main_indicator: acc
ignore_space: False

Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
ext_op_transform_idx: 1
label_file_list:
- ./train_data/train_list.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- RecConAug:
prob: 0.5
ext_data_num: 2
image_shape: [48, 320, 3]
- RecAug:
- MultiLabelEncode:
- RecResizeImg:
image_shape: [3, 48, 320]
- KeepKeys:
keep_keys:
- image
- label_ctc
- label_sar
- length
- valid_ratio
loader:
shuffle: true
batch_size_per_card: 128
drop_last: true
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data
label_file_list:
- ./train_data/val_list.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- MultiLabelEncode:
- RecResizeImg:
image_shape: [3, 48, 320]
- KeepKeys:
keep_keys:
- image
- label_ctc
- label_sar
- length
- valid_ratio
loader:
shuffle: false
drop_last: false
batch_size_per_card: 128
num_workers: 4
131 changes: 131 additions & 0 deletions configs/rec/PP-OCRv3/multi_language/chinese_cht_PP-OCRv3_rec.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,131 @@
Global:
debug: false
use_gpu: true
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/v3_chinese_cht_mobile
save_epoch_step: 3
eval_batch_step: [0, 2000]
cal_metric_during_train: true
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: false
infer_img: doc/imgs_words/ch/word_1.jpg
character_dict_path: ppocr/utils/dict/chinese_cht_dict.txt
max_text_length: &max_text_length 25
infer_mode: false
use_space_char: true
distributed: true
save_res_path: ./output/rec/predicts_ppocrv3_chinese_cht.txt


Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
warmup_epoch: 5
regularizer:
name: L2
factor: 3.0e-05


Architecture:
model_type: rec
algorithm: SVTR
Transform:
Backbone:
name: MobileNetV1Enhance
scale: 0.5
last_conv_stride: [1, 2]
last_pool_type: avg
Head:
name: MultiHead
head_list:
- CTCHead:
Neck:
name: svtr
dims: 64
depth: 2
hidden_dims: 120
use_guide: True
Head:
fc_decay: 0.00001
- SARHead:
enc_dim: 512
max_text_length: *max_text_length

Loss:
name: MultiLoss
loss_config_list:
- CTCLoss:
- SARLoss:

PostProcess:
name: CTCLabelDecode

Metric:
name: RecMetric
main_indicator: acc
ignore_space: False

Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
ext_op_transform_idx: 1
label_file_list:
- ./train_data/train_list.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- RecConAug:
prob: 0.5
ext_data_num: 2
image_shape: [48, 320, 3]
- RecAug:
- MultiLabelEncode:
- RecResizeImg:
image_shape: [3, 48, 320]
- KeepKeys:
keep_keys:
- image
- label_ctc
- label_sar
- length
- valid_ratio
loader:
shuffle: true
batch_size_per_card: 128
drop_last: true
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data
label_file_list:
- ./train_data/val_list.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- MultiLabelEncode:
- RecResizeImg:
image_shape: [3, 48, 320]
- KeepKeys:
keep_keys:
- image
- label_ctc
- label_sar
- length
- valid_ratio
loader:
shuffle: false
drop_last: false
batch_size_per_card: 128
num_workers: 4
131 changes: 131 additions & 0 deletions configs/rec/PP-OCRv3/multi_language/cyrillic_PP-OCRv3_rec.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,131 @@
Global:
debug: false
use_gpu: true
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/v3_cyrillic_mobile
save_epoch_step: 3
eval_batch_step: [0, 2000]
cal_metric_during_train: true
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: false
infer_img: doc/imgs_words/ch/word_1.jpg
character_dict_path: ppocr/utils/dict/cyrillic_dict.txt
max_text_length: &max_text_length 25
infer_mode: false
use_space_char: true
distributed: true
save_res_path: ./output/rec/predicts_ppocrv3_cyrillic.txt


Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
warmup_epoch: 5
regularizer:
name: L2
factor: 3.0e-05


Architecture:
model_type: rec
algorithm: SVTR
Transform:
Backbone:
name: MobileNetV1Enhance
scale: 0.5
last_conv_stride: [1, 2]
last_pool_type: avg
Head:
name: MultiHead
head_list:
- CTCHead:
Neck:
name: svtr
dims: 64
depth: 2
hidden_dims: 120
use_guide: True
Head:
fc_decay: 0.00001
- SARHead:
enc_dim: 512
max_text_length: *max_text_length

Loss:
name: MultiLoss
loss_config_list:
- CTCLoss:
- SARLoss:

PostProcess:
name: CTCLabelDecode

Metric:
name: RecMetric
main_indicator: acc
ignore_space: False

Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
ext_op_transform_idx: 1
label_file_list:
- ./train_data/train_list.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- RecConAug:
prob: 0.5
ext_data_num: 2
image_shape: [48, 320, 3]
- RecAug:
- MultiLabelEncode:
- RecResizeImg:
image_shape: [3, 48, 320]
- KeepKeys:
keep_keys:
- image
- label_ctc
- label_sar
- length
- valid_ratio
loader:
shuffle: true
batch_size_per_card: 128
drop_last: true
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data
label_file_list:
- ./train_data/val_list.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- MultiLabelEncode:
- RecResizeImg:
image_shape: [3, 48, 320]
- KeepKeys:
keep_keys:
- image
- label_ctc
- label_sar
- length
- valid_ratio
loader:
shuffle: false
drop_last: false
batch_size_per_card: 128
num_workers: 4
Loading