Fausto Morales

I support an approach that helps inexperienced users. Experienced users can typically find workarounds like those suggested in this thread. I do wonder under what circumstances a user would rely...

On Windows, this creates another interesting error if you are trying to install `imgaug` while having an open Python process that is using OpenCV. ```bash ERROR: Could not install packages...

Thanks so much for reporting this issue! You are getting this warning because `pipeline.recognize` uses a two-step process where images are first passed through the detector and then the cropped...

First, thanks for all the kind words above! And thank you for your patience -- I usually don't have the cycles to provide thoughtful answers to questions until the weekend...

You are *exactly* right! I've just pushed 95f6209 to fix this.

This is really interesting and a great point. Thank you for sharing the documentation reference. Do you have thoughts on how to resolve? Perhaps we should provide an option for...

Re-opening because we probably ought to fix this so we can get improved inference speed. Not sure when I'll be able to get to it but PRs are welcome!

Hi @mrm8488 -- I do not think it is possible to detect the end of a line directly in the detector or recognizer models. To synthesize word boxes into lines...

Hi there -- your code snippet appears to be missing the part where you run the recognizer. To make it easier for others to reproduce, could you share the *full*...

There is experimental support for an (untrained) EfficientNet backbone which you are able to train with the package. You can use `keras_ocr.detection.Detector(weights=None, backbone_name='EfficientNetB0')`.