Skip to content

Fix pre/post-training evaluation to use same batch in nn_tutorial #3667

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

Fix pre/post-training evaluation to use same batch in nn_tutorial #3667

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
9 changes: 7 additions & 2 deletions beginner_source/nn_tutorial.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -174,6 +174,10 @@ def nll(input, target):
yb = y_train[0:bs]
print(loss_func(preds, yb))

# Save the first batch for comparison after training
xb_initial = xb
yb_initial = yb


###############################################################################
# Let's also implement a function to calculate the accuracy of our model.
Expand Down Expand Up @@ -244,9 +248,10 @@ def accuracy(out, yb):
#
# Let's check the loss and accuracy and compare those to what we got
# earlier. We expect that the loss will have decreased and accuracy to
# have increased, and they have.
# have increased, and they have. We evaluate on the same initial batch
# we used before training for a fair comparison.

print(loss_func(model(xb), yb), accuracy(model(xb), yb))
print(loss_func(model(xb_initial), yb_initial), accuracy(model(xb_initial), yb_initial))

###############################################################################
# Using ``torch.nn.functional``
Expand Down