From 797390d99c7341d225bbb1b02f012411ef81187f Mon Sep 17 00:00:00 2001 From: Prasanth Pulavarthi Date: Tue, 8 Jan 2019 20:15:49 -0800 Subject: [PATCH] Update README.md (#1722) --- README.md | 26 +++++++------------------- 1 file changed, 7 insertions(+), 19 deletions(-) diff --git a/README.md b/README.md index 011a3be8c95..d694a068b83 100644 --- a/README.md +++ b/README.md @@ -5,35 +5,23 @@ |-------|---------| | [![Build Status](https://travis-ci.org/onnx/onnx.svg?branch=master)](https://travis-ci.org/onnx/onnx) | [![Build status](https://ci.appveyor.com/api/projects/status/lm50cevk2hmrll98/branch/master?svg=true)](https://ci.appveyor.com/project/onnx/onnx) | -[Open Neural Network Exchange (ONNX)](http://onnx.ai) is the first step toward an open ecosystem that empowers AI developers -to choose the right tools as their project evolves. ONNX provides an open source format for AI models. -It defines an extensible computation graph model, as well as definitions of built-in operators and standard -data types. Initially we focus on the capabilities needed for inferencing (evaluation). +[Open Neural Network Exchange (ONNX)](http://onnx.ai) is an open ecosystem that empowers AI developers +to choose the right tools as their project evolves. ONNX provides an open source format for AI models, both deep learning and traditional ML. It defines an extensible computation graph model, as well as definitions of built-in operators and standard +data types. Currently we focus on the capabilities needed for inferencing (scoring). -Caffe2, PyTorch, Microsoft Cognitive Toolkit, Apache MXNet and other tools are developing ONNX support. Enabling interoperability between different -frameworks and streamlining the path from research to production will increase the speed of innovation in -the AI community. We are an early stage and we invite the community to submit feedback and help us further -evolve ONNX. +ONNX is [widely supported](http://onnx.ai/supported-tools) and can be found in many frameworks, tools, and hardware. Enabling interoperability between different frameworks and streamlining the path from research to production will increase the speed of innovation in the AI community. We invite the community to join us and further evolve ONNX. # Use ONNX -Start experimenting today: -* [Getting Started Guide](http://onnx.ai/getting-started) -* [Supported Frameworks & Tools](http://onnx.ai/supported-tools) -* [Tutorials on using ONNX converters](https://github.com/onnx/tutorials). +* [Supported Frameworks, Tools, and Hardware](http://onnx.ai/supported-tools) +* [Tutorials for creating ONNX models from](https://github.com/onnx/tutorials). -# Learn about ONNX spec - -Check ONNX design choices and internals: +# Learn about the ONNX spec * [Overview](docs/Overview.md) * [ONNX intermediate representation spec](docs/IR.md) * [Versioning principles of the spec](docs/Versioning.md) * [Operators documentation](docs/Operators.md) * [Python API Overview](docs/PythonAPIOverview.md) -# Tools -* [Netron: a viewer for ONNX models](https://github.com/lutzroeder/Netron) -* [Net Drawer ONNX vizualizer](https://github.com/onnx/tutorials/blob/master/tutorials/VisualizingAModel.md) - # Programming utilities for working with ONNX Graphs * [Shape and Type Inference](docs/ShapeInference.md) * [Graph Optimization](docs/Optimizer.md)