Skip to content

Latest commit

 

History

History
25 lines (19 loc) · 871 Bytes

README.md

File metadata and controls

25 lines (19 loc) · 871 Bytes

Text-Detection-Recognition

setup

If you want to run evaluation on COCO-Text dataset, download and unizip train2014.zip to ./COCO directory.
Then run the following script.

python eval_on_coco_text.py

demo

If you just want ocr on images, run ctpn_crnn_pytorch.py.
PyTorch version of CRNN yields much better result than Tensorflow version.

python ctpn_crnn_pytorch.py

report

For implementation detail or experiment results, refer to the report.

some results