News for hackers. Stuff that matters.
Re:Photos from Crude Sketches: Nvidia's GauGAN Explained Vis... by scoutt on Friday April 12, 2019 @03:34AM (#19642805)
"To reproduce the results reported in the paper, you would need an NVIDIA DGX1 machine with 8 V100 GPUs."
Re:Photos from Crude Sketches: Nvidia's GauGAN Explained Vis... by AdamDKing on Friday April 12, 2019 @04:05AM (#19642952)
That line refers to training the model from scratch. You can still run the trained model very quickly with one "cheap" GPU.

That said, I'm not sure why one wouldn't get a similar result training on the EC2 or GCE instances that have 8 V100s. Or even training with fewer GPUs but accumulating gradients to get the same batch size.