Vishal Gupta

Hi @QtSignalProcessing, great that you did and shared. Could you name the dataset you used, and if it's customized, please describe it and tell the number of classes it has?...

And did you test you model's performance manually on images? How well did it perform? Because the loss reduces even in case of overfitting.

[Here](https://github.com/tyiannak/pyAudioAnalysis/issues/7), the author [Theodoros Giannakopoulos](https://github.com/tyiannak) comments - > **Hi. The whole library has only been tested in Python 2.7**

@bonashen, Does it work, installing using pip? I tried. I got installed but I faced import errors, found no folders.

Hello @mathDR, I need your help. Could you write to me at [email protected]?

@mathDR , I see you've posted only the text recognition code but not region proposal implementaion - how the bounding boxes are found and their numbers are reduced. If you've...

 I'm also not getting an output.

@tangyong after doing the suggested code modification, atleast a window opened with 4 **empty** plot boxes. Could you suggest what would be wrong? I've Windows 8.1, Python 3.5.6.

@d-mo, If specific versions of libraries like Bokeh are required, please do mention, you can see enough such problems in the issues.

@sirfz @dgvogol @Jim-Salmons Do we have a solution yet? Also, maybe this is not appropriate here, but I'm asking. I want to extract texts from an image and convert into...