ONNX

E435223

machine learning file format model exchange format open standard

ONNX (Open Neural Network Exchange) is an open standard format for representing machine learning models that enables interoperability between different deep learning frameworks and tools.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

All labels observed (7)

Label	Occurrences
ONNX canonical	16
ONNX model zoo	2
ONNX IR (Intermediate Representation)	1
ONNX ecosystem	1
ONNX models	1
ONNX operator set	1
Open Neural Network Exchange	1

How this entity was disambiguated

This entity first appeared as the object of triple T4391083 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: ONNX
Context triple: [PlaidML, supportsFramework, ONNX]

A. NVIDIA TensorRT
NVIDIA TensorRT is a high-performance deep learning inference optimizer and runtime library designed to accelerate AI models on NVIDIA GPUs in production environments.
B. NVIDIA Triton Inference Server
NVIDIA Triton Inference Server is an open-source, production-ready platform for serving and scaling AI model inference across GPUs and CPUs with support for multiple frameworks and deployment environments.
C. MXNet
MXNet is an open-source deep learning framework designed for efficient, scalable training and inference across multiple GPUs and distributed systems.
D. PlaidML
PlaidML is an open-source, hardware-agnostic deep learning engine designed to accelerate neural network computation on a wide range of GPUs and other devices.
E. Microsoft Cognitive Toolkit
Microsoft Cognitive Toolkit (CNTK) is an open-source deep learning framework developed by Microsoft for building, training, and deploying neural networks at scale.
F. None of above. chosen
G. Unsure - the case is ambiguous/there is not enough information to decide.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: ONNX
Target entity description: ONNX (Open Neural Network Exchange) is an open standard format for representing machine learning models that enables interoperability between different deep learning frameworks and tools.

A. NVIDIA TensorRT
NVIDIA TensorRT is a high-performance deep learning inference optimizer and runtime library designed to accelerate AI models on NVIDIA GPUs in production environments.
B. NVIDIA Triton Inference Server
NVIDIA Triton Inference Server is an open-source, production-ready platform for serving and scaling AI model inference across GPUs and CPUs with support for multiple frameworks and deployment environments.
C. MXNet
MXNet is an open-source deep learning framework designed for efficient, scalable training and inference across multiple GPUs and distributed systems.
D. PlaidML
PlaidML is an open-source, hardware-agnostic deep learning engine designed to accelerate neural network computation on a wide range of GPUs and other devices.
E. Microsoft Cognitive Toolkit
Microsoft Cognitive Toolkit (CNTK) is an open-source deep learning framework developed by Microsoft for building, training, and deploying neural networks at scale.
F. None of above. chosen

Statements (50)

Predicate	Object
instanceOf	machine learning file format ⓘ model exchange format ⓘ open standard ⓘ
abbreviation	ONNX ⓘ
component	ONNX IR (Intermediate Representation) ⓘ linked to: ONNX ONNX operator set ⓘ linked to: ONNX ONNX runtime implementations ⓘ
dataModel	directed acyclic graph of operators ⓘ
domain	deep learning ⓘ machine learning ⓘ
ecosystem	Caffe2 ⓘ CoreML (via converters) ⓘ MXNet ⓘ Microsoft Cognitive Toolkit (CNTK) ⓘ linked to: Microsoft Cognitive Toolkit ONNX Runtime ⓘ OpenVINO (via import) ⓘ linked to: OpenVINO PyTorch ⓘ TensorFlow (via converters) ⓘ linked to: TensorFlow TensorRT (via parsers) ⓘ linked to: NVIDIA TensorRT scikit-learn (via converters) ⓘ linked to: scikit-learn
enables	deployment across different hardware ⓘ framework-agnostic model serving ⓘ optimization by specialized runtimes ⓘ
fileExtension	.onnx ⓘ
fullName	Open Neural Network Exchange ⓘ linked to: ONNX
governance	community-driven project ⓘ
hasSpecification	graph structure rules ⓘ operator definitions ⓘ tensor type system ⓘ
hasTooling	graph optimizers ⓘ model converters ⓘ model validators ⓘ
hasVersioning	IR versioning ⓘ operator set versioning ⓘ
license	open source specification ⓘ
purpose	enable interoperability between ML frameworks ⓘ facilitate model portability ⓘ represent machine learning models ⓘ
serializationFormat	Protocol Buffers ⓘ
standardType	open ecosystem standard ⓘ
supports	classical machine learning models ⓘ inference ⓘ neural network models ⓘ training export ⓘ
supportsLanguage	C++ APIs (via tooling) ⓘ Python APIs (via tooling) ⓘ
supportsTask	image classification models ⓘ natural language processing models ⓘ object detection models ⓘ speech recognition models ⓘ

How these facts were elicited

Referenced by (23)

Full triples — surface form annotated when it differs from this entity's canonical label.

PlaidML → supportsFramework → ONNX ⓘ

Goya inference processor → compatibleWith → ONNX models ⓘ

linked to: ONNX

ML.NET → supportsModelFormat → ONNX ⓘ

Azure Machine Learning → supports → ONNX ⓘ

MXNet → supportsFormat → ONNX ⓘ

NVIDIA Triton Inference Server → supportsFormat → ONNX ⓘ

NVIDIA TensorRT → supportsModelFormat → ONNX ⓘ

MobileNetV2 → availableInLibrary → ONNX model zoo ⓘ

linked to: ONNX

ShuffleNetV2 → implementedIn → ONNX model zoo ⓘ

linked to: ONNX

ONNX → fullName → Open Neural Network Exchange ⓘ

linked to: ONNX

ONNX → abbreviation → ONNX ⓘ

ONNX → component → ONNX IR (Intermediate Representation) ⓘ

linked to: ONNX

ONNX → component → ONNX operator set ⓘ

linked to: ONNX

Intelligence Processing Unit → supportsFramework → ONNX ⓘ

IPU → supportsFramework → ONNX ⓘ

Poplar SDK → integratesWith → ONNX ⓘ

Qualcomm AI Engine → supportsFramework → ONNX ⓘ

OpenVINO → supportsFramework → ONNX ⓘ

OpenVINO → supportsModelFormat → ONNX ⓘ

ONNX Runtime → supportsFormat → ONNX ⓘ

ONNX Runtime → relatedTo → ONNX ⓘ

ONNX Runtime → partOf → ONNX ecosystem ⓘ

linked to: ONNX

NVIDIA inference platform → supportsModelFormat → ONNX ⓘ

All labels observed (7)

How this entity was disambiguated Show

Statements (50)

How these facts were elicited Show

Referenced by (23)

How this entity was disambiguated

How these facts were elicited