Skip to content

Fix scheduler stepping and label dtype handling in training loop #173

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
likitha487 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix scheduler stepping and label dtype handling in training loop #173

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
5 changes: 2 additions & 3 deletions DeepLense_Classification_Transformers_Archil_Srivastava/train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,8 +44,7 @@ def train_step(model, images, labels, optimizer, scheduler, criterion, device="c
Loss value from the forward pass
"""
# Send to device
images, labels = images.to(device, dtype=torch.float), labels.type(
torch.LongTensor
images, labels = images.to(device, dtype=torch.float), labels.long().to(device)
).to(device)
model.train() # Set train mode
optimizer.zero_grad() # Reset gradients
Expand All @@ -54,7 +53,7 @@ def train_step(model, images, labels, optimizer, scheduler, criterion, device="c
loss.backward() # Backward pass
optimizer.step() # Optimize weights step
if scheduler is not None:
scheduler.step(loss) # Modify learning rate if scheduler is set
scheduler.step() # Modify learning rate if scheduler is set
return loss


Expand Down