You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
from this PR (#859) seems JAX supports grouped convolution (i.e. depthwise separable convolution).
I would like to use it but I have difficulty understanding the related interface. Is there any example for my reference?
Besides this I am interested to know its speed relative to PyTorch/ Tensorflow. I know that (for example) PyTorch doesn't have an optimised implementation of grouped convolution (pytorch/pytorch#18631 (comment)), have anyone done a speed comparison between JAX's grouped convolution against PyTorch/ Tensorflow's equivalent? Thanks!
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
from this PR (#859) seems JAX supports grouped convolution (i.e. depthwise separable convolution).
I would like to use it but I have difficulty understanding the related interface. Is there any example for my reference?
Besides this I am interested to know its speed relative to PyTorch/ Tensorflow. I know that (for example) PyTorch doesn't have an optimised implementation of grouped convolution (pytorch/pytorch#18631 (comment)), have anyone done a speed comparison between JAX's grouped convolution against PyTorch/ Tensorflow's equivalent? Thanks!
Beta Was this translation helpful? Give feedback.
All reactions