Bretislav Hajek

I was testing different input sizes for CTC model, this will be one of them. The shape is in form: `(time_steps, batch_size, image_patch_size)`. The `image_patch_size` is number of pixels exctracted...

Hi, If you want to use those pre-trained models, look into [OCR-Evaluator.ipynb](https://github.com/Breta01/handwriting-ocr/blob/master/OCR-Evaluator.ipynb). These notebook loads two numpy arrays (first contains images of words and second corresponding labels). And it evaluates...

It should work. Please make sure there weren't any errors during download and upload of the file. This error is probably caused by corrupted file.

Can you try to replace the line `csv.field_size_limit(sys.maxsize)` in file `src\ocr\datahelpres.py` with following code: ```python max_int = sys.maxsize while True: # decrease the maxInt value by factor 10 # as...

Oh, that definitely shouldn't take that long (just a few seconds I guess). Did you try setting fixed number like `csv.field_size_limit(2147483647)`?

Well, the steps are bit old and I would like to rework it once I have more time. You have to download datasets according to the instructions in `data/` folder...

It should work now, just pull latest changes from repo.

On what exactly?

First, the issue looks like once again the images aren't loading correctly. CharClassifier is only for taking images of letters (64x64 px) and recognizing them. Please don't mix questions and...

Hi, I expect that you have your own dataset of letters, for training character classifier. In my solution images of letters are loaded from folder `data/charclas/en` where is a folder...