Amit Dovev

We don't support 3rd party tools like pytesseract. We also don't support Tesseract 4.x. Try again with Tesseract 5.2.0.

@ajinkyaG28, Please use our [forum](https://groups.google.com/d/forum/tesseract-ocr) for asking questions.

Do both lstmtraining and lstmeval evaluate exactly the same subset of images+ground truth and in the same order in each evaluation cycle?

This error was also reported in #1012.

+1 for this feature request. After 5.0.0...

The term for converting from int model to float model is `Dequantization` / `Dequantize`. https://www.tensorflow.org/api_docs/python/tf/quantization/dequantize https://pytorch.org/docs/stable/generated/torch.dequantize.html

Which program are you using to view the PDF?

It does not look reversed wtth Chrome PDF viewer, just not very accurate...

@roozgar It seems that Ray is planning to release soon a new version of Tesseract, that will include a new OCR engine based on LSTM. With LSTM, OCR for printed...

> I checked google drive ocr for Arabic and i see it have 100 results for same image.. Neither you or I know what programs they are using to do...