Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
Requirements
- pytorch 1.1
- torchvision 0.3
- pyclipper
- opencv3
Data Preparation
prepare a text in the following format, use '\t' as a separator
/path/to/img.jpg path/to/label.txt
...
Train
- config the
train_data_path
,val_data_path
in config.json - use following script to run
python3 train.py
Test
TBD
Predict
TBD
The project is still under development.
Performance
Method | Precision (%) | Recall (%) | F-measure (%) | FPS(1080Ti) |
---|---|---|---|---|
paper(640*640) | 84.0 | 81.9 | 82.9 | 26.1 |
my implementation | TBD | TBD | TBD | TBD |
ICDAR 2015
TBD
examples
TBD