Bretislav Hajek

Ideas for better propagation - Web page - Docker image - online demo - screencast I am also thinking about adding **tests** and setting up some continuous integration like travis...

Hi @SRK-returns, which branch do you use? The `update` or `master` branch? I don't have any video instructions. It also depends on your OS.

Hi, I am sorry. I forget about this error. Basically, you have to replace all occurrences of `.eval()`. For example this: ```Python accTrain = accuracy.eval(fd) ``` Must be changed into...

I see. I haven't implemented it yet, there were some issues with matching the correct output lengths. You can use `label_err_rate` instead of `accuracy` it is kinda similar, but less...

Great, I would be really thankful for that. I am not really sure about the parameters. Just experiment and you will see.

Hi, This is question depends on the model you want to train. All the notebooks that are for model training contain name Classifier. These notebooks load data from the data...

OK, that's the easy one. The training code is in this notebook: [WordClassifier-CTC.ipynb](https://github.com/Breta01/handwriting-ocr/blob/master/WordClassifier-CTC.ipynb). Currently, the data are loaded from folder `data/words2/` (the location is parametr of `loadWordsData()`). In this folder...

This question is duplicate with #44

Hi, this note is there because sometimes It is not easy to say where should be two letter separated, so I was creating multiple images for each gap. The images...

@yasersakkaf yes you are correct. The problem is that for loading models I am using my custom class `Graph`. This class use operation called `activation` as default output operation in...