Skip to content

add PP-OCRv6_rec #17902

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

Open
zhangyubo0722 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

add PP-OCRv6_rec #17902

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
146 changes: 146 additions & 0 deletions configs/rec/PP-OCRv6/PP-OCRv6_base_rec.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,146 @@
Global:
model_name: PP-OCRv6_base_rec
debug: false
use_gpu: true
epoch_num: 100
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/PP-OCRv6_base_rec
save_epoch_step: 10
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/ppocrv5_dict.txt
max_text_length: &max_text_length 25
infer_mode: false
use_space_char: true
distributed: true
save_res_path: ./output/rec/predicts_ppocrv6_base.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: PPLCNetV4
use_rep: true
stem_type: branch
config_name: base
stem_channels: 128
Head:
name: MultiHead
head_list:
- CTCHead:
Neck:
name: lightsvtr
dims: 192
depth: 3
mlp_ratio: 4.0
local_kernel: 7
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

Train:
dataset:
name: MultiScaleDataSet
ds_width: false
data_dir: ./train_data/
ext_op_transform_idx: 1
label_file_list:
- ./train_data/train_list.txt
ratio_list:
- 0.5
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 64
fix_bs: false
divided_factor: [8, 16]
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: false
drop_last: false
batch_size_per_card: 128
num_workers: 4
141 changes: 141 additions & 0 deletions configs/rec/PP-OCRv6/PP-OCRv6_small_rec.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,141 @@
Global:
model_name: PP-OCRv6_small_rec
debug: false
use_gpu: true
epoch_num: 100
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/PP-OCRv6_small_rec
save_epoch_step: 10
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/ppocrv5_dict.txt
max_text_length: &max_text_length 25
infer_mode: false
use_space_char: true
distributed: true
save_res_path: ./output/rec/predicts_ppocrv6_small.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: PPLCNetV4
use_rep: true
stem_type: branch
Head:
name: MultiHead
head_list:
- CTCHead:
Neck:
name: lightsvtr
dims: 120
depth: 2
mlp_ratio: 2.0
local_kernel: 7
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

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]
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: false
drop_last: false
batch_size_per_card: 128
num_workers: 4
Loading
Loading