Torch downgrade removed from W3D3 (NeuromatchAcademy#905) #934
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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.