githubpiyush

https://github.com/emedvedev/attention-ocr/issues/145#issuecomment-523344851 Go through this link. Let me know if it helps.

https://github.com/emedvedev/attention-ocr/issues/145#issuecomment-523344851 Try this link and repo for testing. Just put all the images in the directory and specify the path in the main.py script.

How is the width is decided? Like which part of the code? Is it learning from previous input's attention or what? Thanks for the response

The Drawing method is "visualize_attention" in model.py file? I want to increase the width because if i can increase the width then characters in my input image can be recognized...

@emedvedev Any updates??

@OctaM Yes that would be really helpful. By the way i have converted most of the part using tf compat v1 and I have stuck when there is hash table...

> It would be great in the meantime to open and pr to a branch intended to work using tensorflow.compat.v1 and fixing tf.contrib dependencies. Or @githubpiyush and @vladdders, was that...

Can you upload your model.h5 file? It would be very helpful.

@lutein any alternative in tensorflow 2?? I was unable to find the _linear function in tensorflow add on.