Re:Andrej Karpathy talks about how Tesla's NNs are structure...
by sgt101 on Sunday November 10, 2019 @03:47AM
(#21497144)
>Nothing crazy about it. TPU-like stuff is ~10x the energy efficiency of GPUs and several times the speed. When you're spending megawatt-hours and days to train a single model, it adds up in both real and opportunity costs.
could you share the stats on this? Google told me to use a K-80 for training.
could you share the stats on this? Google told me to use a K-80 for training.