[FIX] Scaling of empirical/MC Fisher for output with more than two dimensions #109
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Pull Request Test Coverage Report for Build 8961022604Details
💛 - Coveralls |
f-dangel
reviewed
May 3, 2024
Comment on lines
-48
to
+63
| "model_func": lambda: Sequential(Linear(10, 5), ReLU(), Linear(5, 2)), | ||
| "model_func": lambda: Sequential(Linear(10, 5), ReLU(), Linear(5, 3)), | ||
| "loss_func": lambda: CrossEntropyLoss(reduction="mean"), | ||
| "data": lambda: [ | ||
| (rand(3, 10), classification_targets((3,), 2)), | ||
| (rand(4, 10), classification_targets((4,), 2)), | ||
| (rand(3, 10), classification_targets((3,), 3)), | ||
| (rand(4, 10), classification_targets((4,), 3)), | ||
| ], | ||
| "seed": 0, | ||
| }, | ||
| # same as above, but uses reduction='sum' | ||
| { | ||
| "model_func": lambda: Sequential(Linear(10, 5), ReLU(), Linear(5, 2)), | ||
| "model_func": lambda: Sequential(Linear(10, 5), ReLU(), Linear(5, 3)), | ||
| "loss_func": lambda: CrossEntropyLoss(reduction="sum"), | ||
| "data": lambda: [ | ||
| (rand(3, 10), classification_targets((3,), 2)), | ||
| (rand(4, 10), classification_targets((4,), 2)), | ||
| (rand(3, 10), classification_targets((3,), 3)), | ||
| (rand(4, 10), classification_targets((4,), 3)), |
There was a problem hiding this comment.
Any reason why these cases changed?
There was a problem hiding this comment.
Not really, I think I simply preferred having a test case with more than 2 classes, but didn't have a particular failure mode in mind.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Resolves #108.
@f-dangel and me will investigate different definitions for the Fisher in these cases, but for now we will stick to the here implemented convention.