Skip to content

Stop when we reach end_lr even if the loss did not diverge #5

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

Open
Vermeille wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Stop when we reach end_lr even if the loss did not diverge #5

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
3 changes: 2 additions & 1 deletion keras_lr_finder/lr_finder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ def on_batch_end(self, batch, logs):
self.losses.append(loss)

# Check whether the loss got too large or NaN
if math.isnan(loss) or loss > self.best_loss * 4:
if lr >= self.end_lr or math.isnan(loss) or loss > self.best_loss * 4:
self.model.stop_training = True
return

Expand All @@ -40,6 +40,7 @@ def on_batch_end(self, batch, logs):
def find(self, x_train, y_train, start_lr, end_lr, batch_size=64, epochs=1):
num_batches = epochs * x_train.shape[0] / batch_size
self.lr_mult = (end_lr / start_lr) ** (1 / num_batches)
self.end_lr = end_lr

# Save weights into a file
self.model.save_weights('tmp.h5')
Expand Down