Skip to content

fix issue #125 #139

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
mehdidc merged 1 commit into from
Jun 12, 2025
Merged

fix issue #125 #139

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
8 changes: 7 additions & 1 deletion clip_benchmark/metrics/linear_probe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -277,7 +277,13 @@ def evaluate(model, train_dataloader, dataloader, fewshot_k, batch_size, num_wor
peak_idx = find_peak(wd_list, [left, peak_idx, right], feature_train_loader, feature_val_loader, input_shape, output_shape, lr, epochs, autocast, device, verbose, seed)
step_span //= 2
best_wd = wd_list[peak_idx]
train_loader = feature_train_val_loader
if fewshot_k < 0:
# if we are doing full training, we use the full training set (train+val)
train_loader = feature_train_val_loader
else:
# if we are doing few-shot learning, we use the few-shot training set only
# as adding the validation set will train on more data than intended
train_loader = feature_train_loader
else:
best_wd = 0
train_loader = feature_train_loader
Expand Down