Bretislav Hajek

If you want to recognize your handwriting, you first have to train machine learning model for it. In this repo I am trying different models. Personally, I would recommend the...

Yes, that's basically it. You will have to change the OCR.ipynb a little bit, because right now it use a different approach. But that will be quite easy.

Ok, here are the changes. First you have to import `extendImg` function from helpers and change the model that is being loaded. ```Python # Change this line on beginning of...

OK, so now you have 37 images of words (or something else?). In case of words, the best approach would be to tune parameters of already existing model. Try following...

Ok, my mistake, just remove everything which is after training cell. Alse `words_arch` was just name for one of my words datasets. You can raplace it with location of your...

Hi, this is interesting. It looks like the something didn't load. Can you set up try-except, exception catching and print the index, image and gaps. This should point us to...

That is wierd. When I download the data, I see all 53 folders. Also the error is in the line: `images, labels = loadCharsData(charloc='',wordloc='data/words2/',lang=LANG)` Which means that he is using...

First, I forget that the Windows is case insensitive. I will definitely have to save the data in different way. To explain: `images, labels = loadCharsData(charloc=''", wordloc='data/words2/', lang=LANG)` It means...

Well, this is interesting. It looks like issue is in cv2.imread() function behaviour on Windows. On Ubuntu it works fine. I will try to run it on Windows then. There...

Ok, that sounds reasonably. Can you @longwall make the change? I am quite busy during next few weeks.