-
-
Notifications
You must be signed in to change notification settings - Fork 301
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
Adding CLEAR-10 benchmark to Avalanche #965
Conversation
Pull Request Test Coverage Report for Build 2077989484
💛 - Coveralls |
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.
Thank you, the PR looks great! Everything seems to be in order apart from a comment I left regarding transformations.
raise NotImplementedError() | ||
|
||
if feature_type is None: | ||
assert isinstance(train_transform, type(None)), "No image transform" |
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.
I haven't tried to run the code, but from the main below it seems that non-None transformations should be allowed when feature_type is None...
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.
You are right, I should remove the assertion statement (it was a typo). My original purpose is to make sure the user specify a transformation for image, and not inputting a transformation for feature tensors. But on a second thought, I should leave this choice to users!
Made the change by removing assertion statements. |
@lrzpellegrini if you are satisfied we can merge the PR. |
Thanks again @linzhiqiu |
#964 PR for this feature request