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.

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

YOLOV8 Fix modify arch for quantization call #1686

Merged
merged 1 commit into from
Jul 25, 2023
Merged

YOLOV8 Fix modify arch for quantization call #1686

merged 1 commit into from
Jul 25, 2023

Conversation

abhinavnmagic
Copy link
Member

Certain calls for _modify_arch_for_quantization still referred to the class specific implementation which was removed in #1498. The PR fixes the functional calls for all call references.

Test:
a. python -m torch.distributed.run --no_python --nproc_per_node 2 sparseml.ultralytics.train --recipe ~/recipes/yolov8/test_yolov8n_recipe.yaml --model zoo:cv/detection/yolov8-n/pytorch/ultralytics/coco/pruned48_quant-none --data VOC.yaml --batch 4
b. python -m torch.distributed.run --no_python --nproc_per_node 2 sparseml.ultralytics.train --recipe ~/recipes/yolov8/test_yolov8n_recipe.yaml --model runs/detect/train/weights/last.pt --data VOC.yaml --batch 4 --resume

@mgoin
Copy link
Member

mgoin commented Jul 25, 2023

Thank you, LGTM

@mgoin mgoin merged commit ab16210 into main Jul 25, 2023
10 checks passed
@mgoin mgoin deleted the modify_arch_fix branch July 25, 2023 13:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants