Announcing ONNX support for Apache MXNet
Open Neural Network Exchange (ONNX), is an open source format to encode deep learning models. The ONNX-MXNet open source Python package is now available for developers to build and train models with other frameworks such as PyTorch, CNTK, or Caffe2, and import these models into Apache MXNet to run them for inference using MXNet’s highly optimized engine.
Open Neural Network Exchange (ONNX), is an open source format to encode deep learning models. The ONNX-MXNet open source Python package is now available for developers to build and train models with other frameworks such as PyTorch, CNTK, or Caffe2, and import these models into Apache MXNet to run them for inference using MXNet’s highly optimized engine.
ONNX defines the format for the neural network's computational graph, as well as the format for an extensive list of operators used within the graph. With ONNX being supported by an increasing list of frameworks and hardware vendors, developers working on deep learning can move between frameworks easily, picking and choosing the framework that is best suited for the task at hand.
AWS is working with Facebook, Microsoft and the deep learning community to further develop the ONNX format, making it accessible and useful for deep learning practitioners.
MXNet makes it easy for users to import models and run them for inference. Try ONNX using this example from the ONNX-MXNet GitHub repo. Also check out ONNX to dive into how network graph and operators are encoded. Contributions are welcomed!