Closed sitongsu closed 5 years ago
Yes, it looks normal. You can try decrease the depth of convolutional layers which can significantly increase training speed but I am not sure how much the quality of generated images will change.
Yes, it looks normal. You can try decrease the depth of convolutional layers which can significantly increase training speed but I am not sure how much the quality of generated images will change.
thanks for your reply.I will try the decrease in the later experiments
I'm running this model on a computer with TITAN X (Pascal), and my training settings is the same as original. But it takes ~30 seconds/100 iters. Is this running time normal? Here's my output:
Thank you!