Skip to content

Fixed a small bug in metric wrapper #103

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.

Sign up for GitHub

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

Merged
Johanmkr merged 2 commits into from
Feb 24, 2025
Merged

Fixed a small bug in metric wrapper #103

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
603c9be
Fixed a small bug in metric wrapper
Seilmast Feb 24, 2025
bc1dd7a
Removed prints from entropy call func
Seilmast Feb 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CollaborativeCoding/load_metric.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,6 +79,7 @@ def _get_metric(self, key):
raise ValueError(f"Metric {key} not supported")

def __call__(self, y_true, y_pred):
y_true, y_pred = y_true.detach().cpu(), y_pred.detach().cpu()
for key in self.metrics:
self.metrics[key](y_true, y_pred)

Expand Down
3 changes: 0 additions & 3 deletions CollaborativeCoding/metrics/EntropyPred.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,16 +36,13 @@ def __call__(self, y_true: th.Tensor, y_logits: th.Tensor):
assert y_logits.size(-1) == self.num_classes, (
f"y_logit class length: {y_logits.size(-1)}, expected: {self.num_classes}"
)

y_pred = nn.Softmax(dim=1)(y_logits)
print(f"y_pred: {y_pred}")
entropy_values = entropy(y_pred, axis=1)
entropy_values = th.from_numpy(entropy_values)

# Fix numerical errors for perfect guesses
entropy_values[entropy_values == th.inf] = 0
entropy_values = th.nan_to_num(entropy_values)
print(f"Entropy Values: {entropy_values}")
for sample in entropy_values:
self.stored_entropy_values.append(sample.item())

Expand Down