Detecting Text in Natural Image with Connectionist Text Proposal Network
Requirements
- pytorch 1.0
- opencv3
Data Preparation
img
│ 1.jpg
│ 2.jpg
│ ...
gt
│ gt_1.txt
│ gt_2.txt
| ...
Train
- config the
trainroot
,testroot
in config.py - use fellow script to run
python3 train.py
Test
eval.py is used to test model on test dataset
- config
model_path
,data_path
,gt_path
,save_path
in eval.py - use fellow script to test
python3 eval.py
Predict
predict.py is used to inference on single image
- config
model_path
,img_path
,gt_path
,save_path
in predict.py - use fellow script to predict
python3 predict.py
The project is still under development.
Performance
ICDAR 2015
only train on ICDAR2015 dataset with single NVIDIA 1080Ti
my implementation with my loss use adam and warm_up
Method | Precision (%) | Recall (%) | F-measure (%) | FPS(1080Ti) |
---|---|---|---|---|
tbd | tbd | tbd | tbd | tbd |