Laughing ae21eb1abd
Add standalone export functions for onnx and tensorrt formats (#20074)
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2025-04-11 01:54:51 +02:00

21 lines
938 B
Markdown

---
description: Learn how to export PyTorch models to ONNX and TensorRT formats using Ultralytics utilities. Comprehensive guide for configurations, dynamic shapes, and precision optimizations.
keywords: Ultralytics, YOLO, export, ONNX, TensorRT, PyTorch, model conversion, dynamic shapes, FP16, INT8, machine learning
---
# Reference for `ultralytics/utils/export.py`
!!! note
This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/export.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/export.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/export.py) 🛠️. Thank you 🙏!
<br>
## ::: ultralytics.utils.export.export_onnx
<br><br><hr><br>
## ::: ultralytics.utils.export.export_engine
<br><br>