dcorti

Yes, you're right. I extracted the patches randomly, but I did not performed any data augmentation on these patches. Probably some data augmentation, like in the original U-net paper, could...

I tested this code on Python 2.7 only, It needs some modifications to run on python 3.x. Then you need the dependencies listed in the Readme, and of course the...

Hi I have never experienced this issue, but it looks like it is more related to the CUDA and theano libraries. I'm sorry but since I cannot replicate the problem...

Hi Yes, keras keeps updating and therefore many parts of the become obsolete. Please go ahead with the PR, thank you

Hi It looks like the program converged, but indeed the loss function did not decrease significantly. Usually, with the retina DRIVE dataset, the training loss at least halves before flattening....

I'm not sure, since I did strong ovelap as well but it did not create problems. It's hard to guess where the problem could be.