Joel Akeret

Do you have a stacktrace? When does the error happen? What is the shape of your ground truth?

Hard to tell what is causing this. Have you tried to normalize your input?

I was talking about removing the mean and scaling to unit variance. I'm not sure if I understand your case. You have binary input data and you want to learn...

hi @jbitton there might be several reason that the model does not predict anything. Very recently someone found a bug in the `_process_data ` function (#228). Maybe you encounter the...

Once you have trained the network you can get predictions from it without any ground truth

To train the network you need a ground truth (supervised learning). If it's not in the same folder you can either adapt the implementation or write a script to move...

Hi Theo Glad that helped. You could write a for loop from 0 to 9 and always retrieve a single image that you then feed into net.predict. This being said,...

Yes this has been an issue for a while. Could you send me a Pull Request for that?

Due to the network architecture the output prediction are always smaller than the input labels

Hi @haichaoyu thanks for reporting this. 1) I think you're right. The code diverges from the paper architecture. There is no particular reason why I added this. ATM I'm not...