Soumith Chintala

From NVIDIA: 3D support has been added for all layers in CuDNN v3 RC. The story with non-contiguous tensors is somewhat complicated. Short answer is, cuDNN will return CUDNN_STATUS_NOT_SUPPORTED if...

I think it depends on the shape of your latent space. If your latent space is spherical already (i.e. you learnt to sample from a gaussian while training, rather than...

After reading this through, I am convinced that spherical interpolation is essential as well. The weak generations in the center are something I've noticed as well. Thanks for pointing this...

I just spoke to Arthur Szlam who smacked me on the head, because he's been telling this to me for months, and i conveniently ignored it. He says the latent...

So, the hard-wired 64x64 is in the model. Getting around it is actually trivial. Let me write a bit more detailed post, with code references.

Ok, so the data loader is pretty generic. It has two control variables. `opt.loadSize` and `opt.fineSize` [here](https://github.com/soumith/dcgan.torch/blob/master/main.lua#L9-L10). Right now, `loadSize` has to be greater than `fineSize` (because of a bug...

It does indeed seem very similar to actor-critic. There's some trial on doing the network freezing / iterative scheduled optimization. This blog post details some: http://torch.ch/blog/2015/11/13/gan.html#balancing-the-gan-game I've tried it in...

if you want large GANs, look at https://github.com/ajbrock/BigGAN-PyTorch DCGAN is a bit outdated ;-)

there's a way to use kernel=5 and get 64x64, you just force-pad the edges. We did kernel size of 5 in the theano code (because of the way the cudnn...

celebA needs a subfolder with images.