Skip to content
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

Jump to bottom

Fix the batch_idx_train mismatch for model averaging #1757

Merged
merged 1 commit into from
Oct 12, 2024
Merged

Fix the batch_idx_train mismatch for model averaging #1757

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
4 changes: 4 additions & 0 deletions icefall/checkpoint.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -424,8 +424,12 @@ def average_checkpoints_with_averaged_model(
state_dict_start = torch.load(filename_start, map_location=device)
state_dict_end = torch.load(filename_end, map_location=device)

average_period = state_dict_start["average_period"]

batch_idx_train_start = state_dict_start["batch_idx_train"]
batch_idx_train_start = (batch_idx_train_start // average_period) * average_period
batch_idx_train_end = state_dict_end["batch_idx_train"]
batch_idx_train_end = (batch_idx_train_end // average_period) * average_period
interval = batch_idx_train_end - batch_idx_train_start
assert interval > 0, interval
weight_end = batch_idx_train_end / interval
Expand Down
Loading