Is it supposed to be slow?
karamarieliu opened this issue · comments
I'm running on the resized (1,64,64) chairs, and it takes 4.5 hrs to get to 5% of training. I ran with the given values and my cuda() is being used by it.
Pytorch implementation of FactorVAE proposed in Disentangling by Factorising(http://arxiv.org/abs/1802.05983)
karamarieliu opened this issue · comments
I'm running on the resized (1,64,64) chairs, and it takes 4.5 hrs to get to 5% of training. I ran with the given values and my cuda() is being used by it.