metadata
description: >-
Discover how to automatically estimate the best YOLO batch size for optimal
CUDA memory usage in PyTorch using Ultralytics' autobatch utility.
keywords: >-
YOLO batch size, CUDA memory, PyTorch autobatch, Ultralytics, machine
learning, optimal batch size, training batch size, YOLO model
Reference for ultralytics/utils/autobatch.py
!!! note
This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/autobatch.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/autobatch.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/autobatch.py) 🛠️. Thank you 🙏!