Hi Vahid,

Unfortunately when it comes to image-heavy algorithms like GAN, they are very difficult to run in reasonable time on CPU. My best advice would be to try finding a GPU to train the network with. If you need to use a CPU, your options include decreasing image size / kernel size. Another option is to attempt to utilize dilated convolutions to improve performance. Hope you are able to get something working!

PhD. Interests include Deep (Reinforcement) Learning, Computational Neuroscience, and Phenomenology.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store