Open standard for machine learning interoperability

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Your AI software engineering team

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python. ⚠️ ONNX Script is in very early and active development and is not ready for production.

Efficient in-memory representation for ONNX, in Python

Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Staging ground for pytorch/pytorch maintainers to collaborate on release notes for PyTorch releases. Houses the artifacts that chronicle each release.

PyTorch tutorials.

Investigate onnx models

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

Code of the official webpage of onnx

An open-source 3DS emulator project based on Citra.

🤗 Optimum ONNX: Export your model to ONNX and run inference with ONNX Runtime

Repository on the collaborative IVADO medical imaging project between the Mila and NeuroPoly labs.

Prototype of the next torch exporter

The pre- and post processing library for ONNX Runtime

Intro

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

💥Faster R-CNN from scratch written with Keras

Shared repository for open-sourced projects from the Google AI Language team.