Table Of Contents

Deployment

The following tutorials will help you learn how to deploy MXNet on various platforms and in different language environments.

Export

The following tutorials will help you learn export MXNet models.

Export ONNX Modelsonnx.html

How to export an MXNet model to the ONNX model format.

Export with GluonCVhttps://gluon-cv.mxnet.io/build/examples_deployment/export_network.html

How to export models trained with MXNet GluonCV.

Inference

The following tutorials will help you learn how to deploy MXNet models for inference applications.

GluonCV Models in a C++ Inference Applicationhttps://gluon-cv.mxnet.io/build/examples_deployment/cpp_inference.html

An example application that works with an exported MXNet GluonCV YOLO model.

Inference with Quantized Modelshttps://gluon-cv.mxnet.io/build/examples_deployment/int8_inference.html

How to use quantized GluonCV models for inference on Intel Xeon Processors to gain higher performance.

Cloud

The following tutorials will show you how to use MXNet on AWS.

MXNet on EC2run-on-aws/use_ec2.html

How to deploy MXNet on an Amazon EC2 instance.

MXNet on SageMakerrun-on-aws/use_sagemaker.html

How to run MXNet using Amazon SageMaker.

Training with Data from S3https://mxnet.incubator.apache.org/versions/master/faq/s3_integration.html

How to train with data from Amazon S3 buckets.

Security

Securing MXNethttps://mxnet.incubator.apache.org/versions/master/faq/security.html

Best practices and deployment considerations.

Table Of Contents

• Deployment
  • Export
  • Inference
  • Cloud
  • Security

Previous

Accelerated GPU Inference with NVIDIA TensorRT

Next

Export