ONNX
E435223
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.
All labels observed (2)
| Label | Occurrences |
|---|---|
| ONNX canonical | 6 |
| ONNX models | 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 NERFINISHED ⓘ |
| component |
ONNX IR (Intermediate Representation)
NERFINISHED
ⓘ
ONNX operator set NERFINISHED ⓘ ONNX runtime implementations ⓘ |
| dataModel | directed acyclic graph of operators ⓘ |
| domain |
deep learning
ⓘ
machine learning ⓘ |
| ecosystem |
Caffe2
NERFINISHED
ⓘ
CoreML (via converters) ⓘ MXNet NERFINISHED ⓘ Microsoft Cognitive Toolkit (CNTK) NERFINISHED ⓘ ONNX Runtime NERFINISHED ⓘ OpenVINO (via import) NERFINISHED ⓘ PyTorch NERFINISHED ⓘ TensorFlow (via converters) NERFINISHED ⓘ TensorRT (via parsers) NERFINISHED ⓘ scikit-learn (via converters) NERFINISHED ⓘ |
| enables |
deployment across different hardware
ⓘ
framework-agnostic model serving ⓘ optimization by specialized runtimes ⓘ |
| fileExtension | .onnx ⓘ |
| fullName | Open Neural Network Exchange NERFINISHED ⓘ |
| 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 NERFINISHED ⓘ |
| 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
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: ONNX Description of subject: 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.
Referenced by (7)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
ONNX models