Skip to content

Binary accuracy fixes #143

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
merged 2 commits into from
Apr 6, 2018
Merged

Binary accuracy fixes #143

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
09abf08
allow BinaryAccuracy to be computed on GPU
jasonkriss Apr 5, 2018
5db45c2
make it clear that BinaryAccuracy expects probs and not logits
jasonkriss Apr 5, 2018
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
5 changes: 3 additions & 2 deletions ignite/metrics/binary_accuracy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,8 @@ class BinaryAccuracy(Metric):
Calculates the binary accuracy.

`update` must receive output of the form (y_pred, y).
`y_pred` must be in the following shape (batch_size, ...)
`y_pred` must be in the following shape (batch_size, ...) and it's
elements must be between 0 and 1.
`y` must be in the following shape (batch_size, ...)
"""
def reset(self):
Expand All @@ -20,7 +21,7 @@ def reset(self):

def update(self, output):
y_pred, y = output
correct = torch.eq(torch.round(y_pred).type(torch.LongTensor), y).view(-1)
correct = torch.eq(torch.round(y_pred).type(y.type()), y).view(-1)
self._num_correct += torch.sum(correct)
self._num_examples += correct.shape[0]

Expand Down