How to run without using parallelization?

NVlabs / NVAE

The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)

https://arxiv.org/abs/2007.03898

Other

1.02k stars 164 forks source link

How to run without using parallelization? #33

Open working12 opened 2 years ago

working12 commented 2 years ago

Can we run this model without using distributed nature of the code? I simply want to run the code for 1024x1024 images without doing any parallelization? Can't believe I am striggnling with this for a week now.....

ChenLiu-1996 commented 1 year ago

Same issue. No idea how to just use the model for inference, without all the hassles of torch.distributed.