Samples catalog
This page catalogs code samples for ONNX Runtime, running locally, and on Azure, both cloud and edge.
Contents
- Python
- C/C++
- C#
- Java
- Node.js
- Azure Machine Learning
- Huggingface
- Azure IoT Edge
- Azure Media Services
- Azure SQL
- Windows Machine Learning
- ML.NET
Python
- Basic inference
- Resnet50 inference
- Inference samples with ONNX-Ecosystem Docker image
- ONNX Runtime Server: SSD Single Shot MultiBox Detector
- NUPHAR Execution Provider samples
- SKL tutorials
- Keras - Basic
- SSD Mobilenet (Tensorflow)
- BERT-SQuAD (PyTorch) on CPU
- BERT-SQuAD (PyTorch) on GPU
- BERT-SQuAD (Keras)
- BERT-SQuAD (Tensorflow)
- GPT2 (PyTorch)
- EfficientDet (Tensorflow)
- EfficientNet-Edge (Tensorflow)
- EfficientNet-Lite (Tensorflow)
- EfficientNet(Keras)
- MNIST (Keras)
- BERT Quantization on CPU
- Get started with training
- Train NVIDIA BERT transformer model
- Train HuggingFace GPT-2 model
C/C++
- C: SqueezeNet
- C++: model-explorer - single and batch processing
- C++: SqueezeNet
C#
Java
Node.js
Azure Machine Learning
Inference and deploy through AzureML
For aditional information on training in AzureML, please see AzureML Training Notebooks
- Inferencing on CPU using ONNX Model Zoo models:
- Inferencing on CPU with PyTorch model training:
- Inferencing on CPU with model conversion for existing (CoreML) model:
- Inferencing on GPU with TensorRT Execution Provider (AKS):
Huggingface
Azure IoT Edge
Azure Media Services
Azure SQL
Deploy ONNX model in Azure SQL Edge
Windows Machine Learning
Examples of inferencing with ONNX Runtime through Windows Machine Learning
ML.NET
Object Detection with ONNX Runtime in ML.NET