YOLO to ONNX conversion - Revision history

Giuseppe: /* Converting a YOLO Model to ONNX */

2026-06-25T07:55:56Z

Converting a YOLO Model to ONNX

← Older revision		Revision as of 07:55, 25 June 2026
Line 18:		Line 18:
	* Cross-platform model portability.		* Cross-platform model portability.
	* Hardware acceleration when supported by the execution environment.		* Hardware acceleration when supported by the execution environment.



	This is an example of python script that performs the YOLO-to-ONNX conversion:		This is an example of python script that performs the YOLO-to-ONNX conversion:

Giuseppe at 07:55, 25 June 2026

2026-06-25T07:55:45Z

← Older revision		Revision as of 07:55, 25 June 2026
Line 19:		Line 19:
	* Hardware acceleration when supported by the execution environment.		* Hardware acceleration when supported by the execution environment.

	~~== Example~~ of ONNX ~~Conversion Script ==~~		This is an example of python script that performs the YOLO-to-ONNX conversion:

	<syntaxhighlight lang="Python">		<syntaxhighlight lang="Python">

Giuseppe at 07:54, 25 June 2026

2026-06-25T07:54:51Z

← Older revision		Revision as of 07:54, 25 June 2026
Line 21:		Line 21:
	== Example of ONNX Conversion Script ==		== Example of ONNX Conversion Script ==

	<~~highlightsyntax~~ lang="Python">		<syntaxhighlight lang="Python">
	from ultralytics import YOLO		from ultralytics import YOLO

Line 31:		Line 31:
	nms=True		nms=True
	)		)
	</~~highlightsyntax~~>		</syntaxhighlight>

Giuseppe at 07:53, 25 June 2026

2026-06-25T07:53:37Z

← Older revision		Revision as of 07:53, 25 June 2026
Line 18:		Line 18:
	* Cross-platform model portability.		* Cross-platform model portability.
	* Hardware acceleration when supported by the execution environment.		* Hardware acceleration when supported by the execution environment.

			== Example of ONNX Conversion Script ==

			<highlightsyntax lang="Python">
			from ultralytics import YOLO

			model = YOLO("runs/detect/target/weights/best.pt")

			model.export(
			format="onnx",
			simplify=True,
			nms=True
			)
			</highlightsyntax>

Giuseppe: Created page with "= Converting a YOLO Model to ONNX = LogicalDOC performs object detection using the ONNX Runtime Java API. For this reason, trained YOLO models must be converted from the native PyTorch (.pt) format to the Open Neural Network Exchange (ONNX) format before they can be imported into LogicalDOC. ONNX (Open Neural Network Exchange) is an open standard for representing machine learning models. It enables models trained in one framework, such as PyTorch, to be executed effici..."

2026-06-25T07:51:34Z

Created page with "= Converting a YOLO Model to ONNX = LogicalDOC performs object detection using the ONNX Runtime Java API. For this reason, trained YOLO models must be converted from the native PyTorch (.pt) format to the Open Neural Network Exchange (ONNX) format before they can be imported into LogicalDOC. ONNX (Open Neural Network Exchange) is an open standard for representing machine learning models. It enables models trained in one framework, such as PyTorch, to be executed effici..."

New page

= Converting a YOLO Model to ONNX =

LogicalDOC performs object detection using the ONNX Runtime Java API. For this reason, trained YOLO models must be converted from the native PyTorch (.pt) format to the Open Neural Network Exchange (ONNX) format before they can be imported into LogicalDOC.

ONNX (Open Neural Network Exchange) is an open standard for representing machine learning models. It enables models trained in one framework, such as PyTorch, to be executed efficiently in different environments and programming languages.

The conversion process does not retrain or modify the model. Instead, it exports the learned weights and computational graph into a portable format that can be executed by the ONNX Runtime inference engine.

== Why ONNX? ==

Ultralytics trains YOLO models using PyTorch. However, LogicalDOC is implemented in Java and performs inference using the ONNX Runtime library.

Using ONNX provides several advantages:

* No dependency on the Python runtime during inference.
* Native Java support through the ONNX Runtime API.
* Faster startup and lower memory consumption compared to embedding a Python interpreter.
* Cross-platform model portability.
* Hardware acceleration when supported by the execution environment.