Christian Bartz

Yeah you have two options: 1. try to figure out why NCCL is not properly detected while installing cupy (you could try to reinstall cupy with `pip install --upgrade --force-reinstall...

I think Option 1 woked for you because `pip` is a very nasty program when it comes to reinstalling stuff. If you already have installed a package and want to...

oh I see the problem. The code does not work on CPU (unfortunately) and you did not specify which gpu to use (i.e. `-g 0` or `--gpu 0`). If you...

There seems to be something wrong with your arrays. The datatype is not correct, you should check that. Regarding your questions: - STN-OCR and SEE are not the only methods...

this call > File "/home/rohit_shinde12194/see/chainer/models/svhn.py", line 138, in call final_lstm_predictions = F.concat(final_lstm_predictions, axis=0) is the cause of the problem. So just set a breakpoint in this line and have a...

Yes, you are right. This is the lone where the model takes the input data and does the forward pass through the network. It might be a good idea to...

I'd say that something in your train csv is wrong. could you paste the first 3 lines of the label file you are using for training?

that does not look right... in the first line you are stating, that you want to localize a maximum of 4 text lines per image (first 4) and then, that...

Nice, that you got it! I'm sorry it is very difficult to explain properly :sweat_smile:... The `train.csv` file in the `centered` folder is already in the correct format. The first...

Sure, I need the maximum number of lines and maximum number of characters as groundtruth, because of the following reasons: 1. I need to know in advance how many timesteps...