-
Notifications
You must be signed in to change notification settings - Fork 0
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. Weβll occasionally send you account related emails.
Already on GitHub? Sign in to your account
15 run inference on baskerville #30
Conversation
β¦of the custom pipeline method
β¦inputs from being used during inference
β¦cter length of the first language passed to the dataset loader.
β¦der, now save multiple runs under subdirectories named via the seed
β¦nt_result--seed combination directory to exist already, since this is caught in the jobscript creation I don't forsee this being an issue
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.
nice work! A couple of minor changes requested.
@@ -8,6 +11,10 @@ def aggregate_score(probs: torch.Tensor) -> torch.Tensor: | |||
return 1 - torch.mean(distance) | |||
|
|||
|
|||
def zero_one_loss_ceil(y_target, y_pred): |
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 think this is no longer really the zero_one_loss if we're doing a ceil, it's just a ==, so we can remove? or keep it as it was for use over a set of results (rather than single row)
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.
will remove
tests/test_inference.py
Outdated
|
||
dummy_correct_output = [0, 1, 0, 1, 0] | ||
|
||
assert hamming_loss(dummy_target, dummy_correct_output) == pytest.approx( |
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.
we don't need to test sklearn's function so can remove this
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.
Also removed this test
β¦o translation to allow additional confidence measures
Added: