Closed Belval closed 6 years ago
It seems like you forgot to include those lines:
if finish[0, 0] > 0.8:
break
at the end of for
loop, after line 80.
Small advice when using this model, add one space at the end of string you want to generate. I noticed that it sometimes cuts of last character without this space. :)
That did the trick! Thank you
It's quite a weird issue, not sure what might be causing it.
When I run the RNN to get the stroke data, it seems to add some garbage after my input string.
For example:
tsareva becomes Imgur
Here's how I'm using the model: TextRecognitionDataGenerator