This commit is contained in:
@@ -0,0 +1,141 @@
|
||||
Global:
|
||||
model_name: eslav_PP-OCRv5_mobile_rec # To use static model for inference.
|
||||
debug: false
|
||||
use_gpu: true
|
||||
epoch_num: 75
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 10
|
||||
save_model_dir: ./output/eslav_rec_ppocr_v5
|
||||
save_epoch_step: 10
|
||||
eval_batch_step: [0, 1000]
|
||||
cal_metric_during_train: true
|
||||
pretrained_model:
|
||||
checkpoints:
|
||||
save_inference_dir:
|
||||
use_visualdl: false
|
||||
infer_img:
|
||||
character_dict_path: ./ppocr/utils/dict/ppocrv5_eslav_dict.txt
|
||||
max_text_length: &max_text_length 25
|
||||
infer_mode: false
|
||||
use_space_char: true
|
||||
distributed: true
|
||||
save_res_path: ./output/rec/predicts_ppocrv5.txt
|
||||
d2s_train_image_shape: [3, 48, 320]
|
||||
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
lr:
|
||||
name: Cosine
|
||||
learning_rate: 0.0005
|
||||
warmup_epoch: 5
|
||||
regularizer:
|
||||
name: L2
|
||||
factor: 3.0e-05
|
||||
|
||||
|
||||
Architecture:
|
||||
model_type: rec
|
||||
algorithm: SVTR_LCNet
|
||||
Transform:
|
||||
Backbone:
|
||||
name: PPLCNetV3
|
||||
scale: 0.95
|
||||
Head:
|
||||
name: MultiHead
|
||||
head_list:
|
||||
- CTCHead:
|
||||
Neck:
|
||||
name: svtr
|
||||
dims: 120
|
||||
depth: 2
|
||||
hidden_dims: 120
|
||||
kernel_size: [1, 3]
|
||||
use_guide: True
|
||||
Head:
|
||||
fc_decay: 0.00001
|
||||
- NRTRHead:
|
||||
nrtr_dim: 384
|
||||
max_text_length: *max_text_length
|
||||
|
||||
Loss:
|
||||
name: MultiLoss
|
||||
loss_config_list:
|
||||
- CTCLoss:
|
||||
- NRTRLoss:
|
||||
|
||||
PostProcess:
|
||||
name: CTCLabelDecode
|
||||
|
||||
Metric:
|
||||
name: RecMetric
|
||||
main_indicator: acc
|
||||
ignore_space: False
|
||||
|
||||
Train:
|
||||
dataset:
|
||||
name: MultiScaleDataSet
|
||||
ds_width: false
|
||||
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]
|
||||
max_text_length: *max_text_length
|
||||
- RecAug:
|
||||
- MultiLabelEncode:
|
||||
gtc_encode: NRTRLabelEncode
|
||||
- KeepKeys:
|
||||
keep_keys:
|
||||
- image
|
||||
- label_ctc
|
||||
- label_gtc
|
||||
- length
|
||||
- valid_ratio
|
||||
sampler:
|
||||
name: MultiScaleSampler
|
||||
scales: [[320, 32], [320, 48], [320, 64]]
|
||||
first_bs: &bs 128
|
||||
fix_bs: false
|
||||
divided_factor: [8, 16] # w, h
|
||||
is_training: True
|
||||
loader:
|
||||
shuffle: true
|
||||
batch_size_per_card: *bs
|
||||
drop_last: true
|
||||
num_workers: 8
|
||||
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:
|
||||
gtc_encode: NRTRLabelEncode
|
||||
- RecResizeImg:
|
||||
image_shape: [3, 48, 320]
|
||||
- KeepKeys:
|
||||
keep_keys:
|
||||
- image
|
||||
- label_ctc
|
||||
- label_gtc
|
||||
- length
|
||||
- valid_ratio
|
||||
loader:
|
||||
shuffle: true
|
||||
drop_last: false
|
||||
batch_size_per_card: 128
|
||||
num_workers: 4
|
||||
@@ -0,0 +1,141 @@
|
||||
Global:
|
||||
model_name: korean_PP-OCRv5_mobile_rec # To use static model for inference.
|
||||
debug: false
|
||||
use_gpu: true
|
||||
epoch_num: 75
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 10
|
||||
save_model_dir: ./output/korean_rec_ppocr_v5
|
||||
save_epoch_step: 10
|
||||
eval_batch_step: [0, 1000]
|
||||
cal_metric_during_train: true
|
||||
pretrained_model:
|
||||
checkpoints:
|
||||
save_inference_dir:
|
||||
use_visualdl: false
|
||||
infer_img:
|
||||
character_dict_path: ./ppocr/utils/dict/ppocrv5_korean_dict.txt
|
||||
max_text_length: &max_text_length 25
|
||||
infer_mode: false
|
||||
use_space_char: true
|
||||
distributed: true
|
||||
save_res_path: ./output/rec/predicts_ppocrv5.txt
|
||||
d2s_train_image_shape: [3, 48, 320]
|
||||
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
lr:
|
||||
name: Cosine
|
||||
learning_rate: 0.0005
|
||||
warmup_epoch: 5
|
||||
regularizer:
|
||||
name: L2
|
||||
factor: 3.0e-05
|
||||
|
||||
|
||||
Architecture:
|
||||
model_type: rec
|
||||
algorithm: SVTR_LCNet
|
||||
Transform:
|
||||
Backbone:
|
||||
name: PPLCNetV3
|
||||
scale: 0.95
|
||||
Head:
|
||||
name: MultiHead
|
||||
head_list:
|
||||
- CTCHead:
|
||||
Neck:
|
||||
name: svtr
|
||||
dims: 120
|
||||
depth: 2
|
||||
hidden_dims: 120
|
||||
kernel_size: [1, 3]
|
||||
use_guide: True
|
||||
Head:
|
||||
fc_decay: 0.00001
|
||||
- NRTRHead:
|
||||
nrtr_dim: 384
|
||||
max_text_length: *max_text_length
|
||||
|
||||
Loss:
|
||||
name: MultiLoss
|
||||
loss_config_list:
|
||||
- CTCLoss:
|
||||
- NRTRLoss:
|
||||
|
||||
PostProcess:
|
||||
name: CTCLabelDecode
|
||||
|
||||
Metric:
|
||||
name: RecMetric
|
||||
main_indicator: acc
|
||||
ignore_space: False
|
||||
|
||||
Train:
|
||||
dataset:
|
||||
name: MultiScaleDataSet
|
||||
ds_width: false
|
||||
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]
|
||||
max_text_length: *max_text_length
|
||||
- RecAug:
|
||||
- MultiLabelEncode:
|
||||
gtc_encode: NRTRLabelEncode
|
||||
- KeepKeys:
|
||||
keep_keys:
|
||||
- image
|
||||
- label_ctc
|
||||
- label_gtc
|
||||
- length
|
||||
- valid_ratio
|
||||
sampler:
|
||||
name: MultiScaleSampler
|
||||
scales: [[320, 32], [320, 48], [320, 64]]
|
||||
first_bs: &bs 128
|
||||
fix_bs: false
|
||||
divided_factor: [8, 16] # w, h
|
||||
is_training: True
|
||||
loader:
|
||||
shuffle: true
|
||||
batch_size_per_card: *bs
|
||||
drop_last: true
|
||||
num_workers: 8
|
||||
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:
|
||||
gtc_encode: NRTRLabelEncode
|
||||
- RecResizeImg:
|
||||
image_shape: [3, 48, 320]
|
||||
- KeepKeys:
|
||||
keep_keys:
|
||||
- image
|
||||
- label_ctc
|
||||
- label_gtc
|
||||
- length
|
||||
- valid_ratio
|
||||
loader:
|
||||
shuffle: true
|
||||
drop_last: false
|
||||
batch_size_per_card: 128
|
||||
num_workers: 4
|
||||
@@ -0,0 +1,143 @@
|
||||
Global:
|
||||
model_name: latin_PP-OCRv5_mobile_rec # To use static model for inference.
|
||||
debug: false
|
||||
use_gpu: true
|
||||
epoch_num: 75
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 10
|
||||
save_model_dir: ./output/latin_rec_ppocr_v5
|
||||
save_epoch_step: 10
|
||||
eval_batch_step: [0, 500]
|
||||
cal_metric_during_train: true
|
||||
pretrained_model: PP-OCRv5_mobile_rec_pretrained.pdparams
|
||||
checkpoints:
|
||||
save_inference_dir:
|
||||
use_visualdl: false
|
||||
infer_img:
|
||||
character_dict_path: ./ppocr/utils/dict/ppocrv5_latin_dict.txt
|
||||
infer_mode: false
|
||||
use_space_char: true
|
||||
distributed: true
|
||||
save_res_path: ./output/rec/predicts_ppocrv5.txt
|
||||
d2s_train_image_shape: [3, 48, 320]
|
||||
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
lr:
|
||||
name: Cosine
|
||||
learning_rate: 0.0005
|
||||
warmup_epoch: 5
|
||||
regularizer:
|
||||
name: L2
|
||||
factor: 3.0e-05
|
||||
|
||||
|
||||
Architecture:
|
||||
model_type: rec
|
||||
algorithm: SVTR_LCNet
|
||||
Transform:
|
||||
Backbone:
|
||||
name: PPLCNetV3
|
||||
scale: 0.95
|
||||
Head:
|
||||
name: MultiHead
|
||||
head_list:
|
||||
- CTCHead:
|
||||
Neck:
|
||||
name: svtr
|
||||
dims: 120
|
||||
depth: 2
|
||||
hidden_dims: 120
|
||||
kernel_size: [1, 3]
|
||||
use_guide: True
|
||||
Head:
|
||||
fc_decay: 0.00001
|
||||
- NRTRHead:
|
||||
nrtr_dim: 384
|
||||
max_text_length: 25
|
||||
|
||||
Loss:
|
||||
name: MultiLoss
|
||||
loss_config_list:
|
||||
- CTCLoss:
|
||||
- NRTRLoss:
|
||||
|
||||
PostProcess:
|
||||
name: CTCLabelDecode
|
||||
|
||||
Metric:
|
||||
name: RecMetric
|
||||
main_indicator: acc
|
||||
ignore_space: False
|
||||
|
||||
Train:
|
||||
dataset:
|
||||
name: MultiScaleDataSet
|
||||
ds_width: false
|
||||
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]
|
||||
max_text_length: 25
|
||||
- RecAug:
|
||||
- MultiLabelEncode:
|
||||
max_text_length: 25
|
||||
gtc_encode: NRTRLabelEncode
|
||||
- KeepKeys:
|
||||
keep_keys:
|
||||
- image
|
||||
- label_ctc
|
||||
- label_gtc
|
||||
- length
|
||||
- valid_ratio
|
||||
sampler:
|
||||
name: MultiScaleSampler
|
||||
scales: [[320, 32], [320, 48], [320, 64]]
|
||||
first_bs: &bs 128
|
||||
fix_bs: false
|
||||
divided_factor: [8, 16] # w, h
|
||||
is_training: True
|
||||
loader:
|
||||
shuffle: true
|
||||
batch_size_per_card: *bs
|
||||
drop_last: true
|
||||
num_workers: 8
|
||||
Eval:
|
||||
dataset:
|
||||
name: SimpleDataSet
|
||||
data_dir: ./train_data/
|
||||
label_file_list:
|
||||
- ./train_data/eval_list.txt
|
||||
transforms:
|
||||
- DecodeImage:
|
||||
img_mode: BGR
|
||||
channel_first: false
|
||||
- MultiLabelEncode:
|
||||
max_text_length: 1000
|
||||
gtc_encode: NRTRLabelEncode
|
||||
- RecResizeImg:
|
||||
eval_mode: True
|
||||
image_shape: [3, 48, 320]
|
||||
- KeepKeys:
|
||||
keep_keys:
|
||||
- image
|
||||
- label_ctc
|
||||
- label_gtc
|
||||
- length
|
||||
- valid_ratio
|
||||
loader:
|
||||
shuffle: false
|
||||
drop_last: false
|
||||
batch_size_per_card: 1
|
||||
num_workers: 4
|
||||
Reference in New Issue
Block a user