WenmuZhou/PytorchOCR
A PyTorch implementation of OCR models converting PaddleOCR weights for text detection and recognition tasks.
Not currently ranked — collecting fresh signals.
star history
Provides a PyTorch implementation of OCR (Optical Character Recognition) models, primarily converting models from PaddleOCR to PyTorch format. Includes support for text detection and recognition algorithms with training, evaluation, inference, and model export capabilities. Covers PP-OCR series models including v3 and v4 variants.
Frequently asked
- What is WenmuZhou/PytorchOCR?
- A PyTorch implementation of OCR models converting PaddleOCR weights for text detection and recognition tasks.
- Is PytorchOCR open source?
- Yes — WenmuZhou/PytorchOCR is an open-source project tracked on heatdrop.
- What language is PytorchOCR written in?
- WenmuZhou/PytorchOCR is primarily written in Python.
- How popular is PytorchOCR?
- WenmuZhou/PytorchOCR has 1.5k stars on GitHub.
- Where can I find PytorchOCR?
- WenmuZhou/PytorchOCR is on GitHub at https://github.com/WenmuZhou/PytorchOCR.