AI Notebooks - Tutorial - Fine-Tune and export an AI model to ONNX

Objective

The aim of this tutorial is to show you how to Fine-Tune a PyTorch model and export it in ONNX (Open Neural Network Exchange) format.

For this purpose, we use an image classification model: DenseNet.

The goal is to Fine-Tune a DenseNet121 model to classify daily life images with the CIFAR-10 dataset. It is composed of 10 classes:

• airplane
• automobile
• bird
• cat
• deer
• dog
• frog
• horse
• ship
• truck

Find out more information about CIFAR-10 dataset on the following link.

At the end of training, the DenseNet model is saved in PyTorch format (.pth). It will then be transformed into ONNX.

Exporting your model in ONNX format allows you to optimize the inference of a Machine Learning model.

Requirements

• Access to the OVHcloud Control Panel
• An AI Notebooks project created inside a Public Cloud project in your OVHcloud account
• A user for AI Notebooks
• A Kaggle account to download the dataset

Instructions

You can launch the notebook from the OVHcloud Control Panel or via the ovhai CLI.

Launching a Jupyter notebook with "Conda" via UI (Control Panel)

To launch your notebook from the OVHcloud Control Panel, refer to the following steps.

Code editor

Choose the Jupyterlab code editor.

Framework

In this tutorial, the conda framework is used.

Resources

Using GPUs is recommended to train the image classification model: densenet121.

Launching a Jupyter notebook with "conda" via CLI

If you do not use our CLI yet, follow this guide to install it.

If you want to launch your notebook with the OVHcloud AI CLI, choose the jupyterlab editor and the conda framework.

To access the different versions of conda available, run the following command:

ovhai capabilities framework get conda -o yaml

You will also need to choose the number of GPUs to use in your notebook, using <nb-gpus>.

To launch your notebook, run the following command:

ovhai notebook run conda jupyterlab \
        --name <notebook-name> \
        --framework-version conda-py310-cuda11.8-v22-4 \
        --gpu <nb-gpus>

You can then reach your notebook’s URL once the notebook is running.

Accessing the notebooks

Once our AI examples repository has been cloned in your environment, find the fine-tuning notebook tutorial by following this path: ai-training-examples > notebooks > go-further > onnx > notebook_finetune_densenet_export_onnx.ipynb.

A preview of this notebook can be found on GitHub here.

Go further

There are many other tasks that exist in the computer vision field. Check our other tutorials to learn how to:

• Use Transfer Learning with ResNet50 for image classification

• Perform Brain tumor segmentation using U-Net

If you need training or technical assistance to implement our solutions, contact your sales representative or click on this link to get a quote and ask our Professional Services experts for a custom analysis of your project.

Feedback

Please send us your questions, feedback and suggestions to improve the service:

• On the OVHcloud Discord server