Is it supposed to be slow?

1Konny / FactorVAE

Pytorch implementation of FactorVAE proposed in Disentangling by Factorising(http://arxiv.org/abs/1802.05983)

MIT License

262 stars 48 forks source link

Is it supposed to be slow? #12

Open karamarieliu opened 4 years ago

karamarieliu commented 4 years ago

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.