Bretislav Hajek

What did you try to install? You should run: `pip install pyenchant`. I just found out, that it's no longer under maintenance. I will try to replace it.

Yes, it is because CTC model requires little bit different inputs. OCR notebook right now works only with char classifier. Take a look into `ocr_evaluator.ipynb` at `class WordCycler()`. I hope...

In this repo, there are tested two main approaches of words recognition. In first, the images of words are processed by gap classifier (separates word into individual letters). Then individual...

If you are speaking about text extraction from images. I guess that the prescription forms will have some kind of structure. Once you have an image of prescription, you can...

Hi @xiaolele11, thanks for letting me know. You just have to add following line to the code: ```LOSS_ITER = 150 # number states that every 150 steps it will print...

No problem. This is not really necessary for training, but you can solve it by adding: ```Python test_targets = tf.sparse_tensor_to_dense(targets) ``` Add it somewhere in the model definition, ideally after...

First, look into the data folder. There should be instructions how to download the datasets. Then you have to process the data and create the csv files. The processing scripts...

I should probably create some documentation in GitHub Wikis. Anyway, there are two options how to create a dataset for the CharClassifier. Both options uses `loadCharsData()` function. This function takes...

Sure, just save the outputed strings into file.

I have same error. I guess it is related to changes in `boto3` library. My solution is adding file `~/.aws/config` with content: ```ini [default] region=us-east-1 ``` You will be able...