CRNN, proposed by Baoguang Shi et al. in 2015, is a combination of CNN, RNN and CTC loss for image-based sequence recognition tasks, such as scene text recognition and OCR.
| Model | Download |
|---|---|
| CRNN(pytorch) | 32MB |
| CRNN(ONNX) | 32MB |
- An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
- meijieru/crnn.pytorch
- bgshih/crnn
MIT