Skip to content

Fix CNN prediction threshold for binary classification #14902

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

Closed
ParikshitGupta2605 wants to merge 1 commit into from
Closed

Fix CNN prediction threshold for binary classification #14902

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 4 additions & 2 deletions computer_vision/cnn_classification.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,9 @@
test_image = np.expand_dims(test_image, axis=0)
result = classifier.predict(test_image)
# training_set.class_indices
if result[0][0] == 0:
# The sigmoid output is a probability in the range [0, 1].
# Use a threshold of 0.5 to convert the probability into a binary prediction.
if result[0][0] < 0.5:
prediction = "Normal"
if result[0][0] == 1:
else:
prediction = "Abnormality detected"

Check failure on line 102 in computer_vision/cnn_classification.py

View workflow job for this annotation

GitHub Actions / ruff

ruff (SIM108) 

computer_vision/cnn_classification.py:99:5: SIM108 Use ternary operator `prediction = "Normal" if result[0][0] < 0.5 else "Abnormality detected"` instead of `if`-`else`-block
  help: Replace `if`-`else`-block with `prediction = "Normal" if result[0][0] < 0.5 else "Abnormality detected"`
Loading