- Notifications
You must be signed in to change notification settings - Fork134
A pure pytorch implemented ocr project including text detection and recognition
License
courao/ocr.pytorch
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
A pure pytorch implemented ocr project.
Text detection is based CTPN and text recognition is based CRNN.
More detection and recognition methods will be supported!
- python-3.5+
- pytorch-0.4.1+
- torchvision-0.2.1
- opencv-3.4.0.14
- numpy-1.14.3
They could all be installed through pip except pytorch and torchvision. As for pytorch and torchvision,they both depends on your CUDA version, you would prefer to readingpytorch's official site
Detection is based onCTPN, some codes are borrowed frompytorch_ctpn, several detection results:
Recognition is based onCRNN, some codes are borrowed fromcrnn.pytorch
Download pretrained models fromBaidu Netdisk (extract code: u2ff) orGoogle Driverand put these files into checkpoints.Then run
python3 demo.py
The image files in ./test_images will be tested for text detection and recognition, the results will be stored in ./test_result.
If you want to test a single image, run
python3 test_one.py [filename]
Training codes are placed into train_code directory.
TrainCTPN
TrainCRNN