-
Notifications
You must be signed in to change notification settings - Fork 3.4k
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
Support torchtext on a single GPU #2379
Support torchtext on a single GPU #2379
Conversation
@mateuszpieniak I wonder why torchtext.Batch doesn't have a .to() method. Wouldn't that be a logical choice? It seems so obvious. It would make the support much easier. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
awesome! let's finalize the changes requested so we can merge :) |
|
@@ -7,3 +7,4 @@ tensorboard>=1.14 | |||
future>=0.17.1 # required for builtins in setup.py | |||
# pyyaml>=3.13 | |||
PyYAML>=5.1 # OmegaConf requirement | |||
torchtext>=0.3.1 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Torchtext as mandatory dependency? When we refused torchvision.... @williamFalcon
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
agree, should go to extras. I was not fast enough to properly review :(
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
fixing in #2395
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
sorry, didn't catch that. i thought it was in extras
What does this PR do?
Allows using torchtext on a single GPU e.g. via
torch.text.BucketIterator
object which in turn generatetorchtext.data.Batch
objects. It seems like it works only on a single GPU due to #2350.Fixes #1245
Before submitting
PR review
Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.
Did you have fun?
Make sure you had fun coding 🙃