Skip to content

[draft] init fine tune #17724

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
sidaluminx wants to merge 1 commit into
base: main
Choose a base branch
from
+10 −10
Open

[draft] init fine tune #17724

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
20 changes: 10 additions & 10 deletions configs/rec/PP-OCRv5/PP-OCRv5_server_rec.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,15 +2,15 @@ Global:
model_name: PP-OCRv5_server_rec # To use static model for inference.
debug: false
use_gpu: true
epoch_num: 75
epoch_num: 10
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/PP-OCRv5_server_rec
save_epoch_step: 1
eval_batch_step: [0, 2000]
eval_batch_step: [0, 4]
cal_metric_during_train: true
calc_epoch_interval: 1
pretrained_model:
pretrained_model: pretrained_models/PP-OCRv5_server_rec_pretrained.pdparams
checkpoints:
save_inference_dir:
use_visualdl: false
Expand All @@ -19,7 +19,7 @@ Global:
max_text_length: &max_text_length 25
infer_mode: false
use_space_char: true
distributed: true
distributed: false
save_res_path: ./output/rec/predicts_ppocrv5.txt
d2s_train_image_shape: [3, 48, 320]

Expand All @@ -30,8 +30,8 @@ Optimizer:
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.0005
warmup_epoch: 1
learning_rate: 0.000000000
warmup_epoch: 0
regularizer:
name: L2
factor: 3.0e-05
Expand Down Expand Up @@ -78,10 +78,10 @@ Train:
dataset:
name: MultiScaleDataSet
ds_width: false
data_dir: ./train_data/
data_dir: .
ext_op_transform_idx: 1
label_file_list:
- ./train_data/train_list.txt
- ./bbox_gemini_out/train_list.txt
transforms:
- DecodeImage:
img_mode: BGR
Expand Down Expand Up @@ -111,9 +111,9 @@ Train:
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data
data_dir: .
label_file_list:
- ./train_data/val_list.txt
- ./bbox_gemini_out/val_list.txt
transforms:
- DecodeImage:
img_mode: BGR
Expand Down