search

dyelax / Adversarial_Video_Generation

A TensorFlow Implementation of "Deep Multi-Scale Video Prediction Beyond Mean Square Error" by Mathieu, Couprie & LeCun.
MIT License
735 stars 184 forks source link

Value error in scikit image #4

Open Vishal-Upendran opened 7 years ago

Vishal-Upendran commented 7 years ago

Hi,

I was trying out the code, and obtained a scikit value error: float should be between -1 and 1. I found out in /utils.py of function get_train_batch(), Line 126, the clip is defined to be float32, but it apparently causes the range error, and changed it to float64. It works now. Is it due to some version of dependency or scikit, etc?

Thanks,

Vishal

dyelax commented 7 years ago

Hmm, which version of scipy do you have? I am on version 0.16.1 and I'm not getting that error.

martinosorb commented 6 years ago

I have the same problem. If you just read the code, you can easily see how to fix it. Remove the transformation from (-1, 1) to (0, 1). After doing that, I still get some values above 1, which is a bit strange. But because they're very slightly above 1, I just clipped them and ignored the issue.