Skip to content
This repository was archived by the owner on Jun 4, 2025. It is now read-only.

Commit 9bad268

Browse files
authored
[fix] remove image_size from call to rescale_gradient_accumulation (#202) (#203)
#200 included a side change to remove the now unused `image_size` arg from the function signature but did not update the call site. this PR fixes that. **test_plan:** Reproduced reported error with a sample quantization recipe and verified this PR resolves it
1 parent 541d003 commit 9bad268

File tree

1 file changed

+0
-1
lines changed

1 file changed

+0
-1
lines changed

train.py

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -314,7 +314,6 @@ def _create_dataloaders():
314314
new_batch_size, new_accumulate = sparsification_manager.rescale_gradient_accumulation(
315315
batch_size=batch_size,
316316
accumulate=accumulate,
317-
image_size=imgsz
318317
)
319318
if new_batch_size != batch_size:
320319
batch_size = new_batch_size

0 commit comments

Comments
 (0)