-
Notifications
You must be signed in to change notification settings - Fork 21.3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Which backprop method is correct for RNN? #635
Comments
You've used the same model twice. You probably meant to use |
Sorry about that. Thanks! |
zou3519
pushed a commit
to zou3519/pytorch
that referenced
this issue
Mar 30, 2018
mrshenli
pushed a commit
to mrshenli/pytorch
that referenced
this issue
Apr 11, 2020
Reorder text tutorials
mcarilli
pushed a commit
to mcarilli/pytorch
that referenced
this issue
Feb 2, 2021
Summary: CUDA TK >= 11.1 provides ptxjitcompiler that emits SASS instead of PTX. 1. This gives better backward-compatibility that allows future TK to work with older driver, which might not necessarily be able to load generated PTX through JIT compile and would error out at runtime; https://docs.nvidia.com/deploy/cuda-compatibility/#using-ptx 2. Meanwhile, SASS doesn't provide good future compatibility, so for unsupported arch, we fallback to PTX to support future device. https://docs.nvidia.com/deploy/cuda-compatibility/index.html#cubin-compatibility Pull Request resolved: pytorch#50319 Reviewed By: malfet Differential Revision: D26114475 Pulled By: ngimel fbshipit-source-id: 046e9e7b3312d910f499572608a0bc1fe53feef5
KyleCZH
pushed a commit
to KyleCZH/pytorch
that referenced
this issue
Sep 20, 2021
Signed-off-by: Eli Uriegas <eliuriegas@fb.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Accumulating loss incrementally with timestep as in the tutorial, and sending all tiemsteps to RNN seem to produce the same output/hidden/loss but loss.backwards is calculating different parameter gradients. Is there a correct and incorrect method to do this? Which is right?
The text was updated successfully, but these errors were encountered: