megalinier

Hello, I do get the same problem : running your program without changing anything, I get a high accuracy, but the predictions on the random samples are all different from...

Hey, I think the code for the printing of the random samples has some mistake in it, indeed, but the rest of the algorithm is good =) If you want...

Thank you for your answer. After some modifications of your programs, I was finally able to apply the 2D transform to images with different channels =) I am not sure...

I didn't find the way to upload directly the scripts... So here are all the (partially modified) functions that make the multi-channel computations possible. You can replace all the functions...