Closed colleenjg closed 8 months ago
Tagging @spirosChv to let you know about this PR reversing the torch
downgrade you implemented a few months ago to fix a new memory bug that showed up in W3D3. :)
TL;DR: torch
on Google Colab has now been updated to 2.1
. From my tests, this fixes the memory bug you found (as planned!), and so torch
no longer needs to be downgraded.
This commit fixes issue #905.
torch 2.0
introduced an out of memory bug in the tutorial, which was addressed with commit ed8f9f2 by downgrading totorch 1.11
. The pytorch bug was fixed intorch 2.1
through commit fff4a9. Since Google Colab now comes withtorch 2.1
installed by default, the downgrade is no longer needed.I also changed the supervised learning performance reported in table from
98.67%
to98.70%
. Unlike the other methods (VAE, SimCLR, etc.), the supervised result has never been perfectly identical on each run. It varies a little bit around98.70%
(from98.67%
to98.73%
, when I've run it). To avoid confusion for users, the first time this result is reported, it is now reported with a~
(i.e., as~98.70%
) to signal to users that their result may differ slightly from it.