Have a model with ONNX format what framework should i use?

Question

I have a model which does the inference for a batch of images using the branch transform. And my model is stored in s3 bucket ,Now my question is what frame or the base container image should i be using for this model, if possible please let me know the instance type as well.

rePost-User-9309630 · Answer

## ONNX framework

ONNX is supported by popular deep learning frameworks such as Apache MXNet, PyTorch, Chainer, Cognitive Toolkit, TensorRT, and others.

And through this [blog](https://aws.amazon.com/blogs/machine-learning/aws-deep-learning-amis-now-include-onnx-enabling-model-portability-across-deep-learning-frameworks/), you can learn about the process of importing ONNX models into MXNet.

## Base Container Image

The AWS Deep Learning AMIs (DLAMI) for Ubuntu and Amazon Linux are now pre-installed and fully configured with Open Neural Network Exchange (ONNX), enabling model portability across deep learning frameworks.

The EC2 AMI catalog provides AMIs categorized by framework:
![Enter image description here](/media/postImages/original/IMi8GmENjBR6ujPmXYa2vOQw)

## Instance Type

For inference, it's recommended to consider GPU instances. For example, I suggest the P-series or G-series. The exact instance type may vary depending on the size of the model and the data to be processed. You can check the number of GPUs, memory, and pricing information on this [page](https://aws.amazon.com/ec2/instance-types/#accelerated-computing).

Have a model with ONNX format what framework should i use?

ONNX framework

Base Container Image

Instance Type

Add your answer

Relevant content