After JS fatigue: deep learning fatigue.
-
@fchollet running mnist_cnn on the Jetson tk1. It's a lot slower than a standard cpu. Have you seen anything like this?
@dmarthal 1) make sure you have cuDNN installed (and being used) 2) increase batch size to ~1024
-
-
@fchollet That did the trick! mnist_cnn.py ran taking about 158s for each epoch. Not bad! CPU was about 870s.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.