--- title: "AI Notebooks - Tutorial - Use ResNet for image classification" description: "How to use an existing model to do Transfer Learning?" url: https://docs.ovhcloud.com/it/guides/public-cloud/ai-machine-learning/ai-notebooks-transfer-learning-resnet lang: it lastUpdated: 2022-09-01 --- # AI Notebooks - Tutorial - Use ResNet for image classification ## Objective This tutorial will allow you to use **Transfer Learning** to train an existing model on a custom dataset thanks to **OVHcloud AI Notebooks**. To show how Transfer Learning can be useful, **ResNet50** will be trained on a custom dataset. ### USE CASE: Flower Classification :::info To classify flower images, the **Flower Classification** dataset will be used. It is available on [Kaggle](https://www.kaggle.com/datasets/sauravagarwal/flower-classification). ::: _Contains information from [Flower Classification](https://www.kaggle.com/datasets/sauravagarwal/flower-classification), which is made available here under the [CC0: Public Domain](https://creativecommons.org/publicdomain/zero/1.0/)._ ## Definition ### Transfer learning In Machine Learning, the aim of **Transfer Learning** is to use the knowledge already acquired to solve a completely new, but related problem. In other words, the technique is to transfer the notions learned on a source dataset to be more efficient in the processing of a new target dataset. For this tutorial, the goal is to do **image classification**. An existing model is used: **ResNet50**. ### ResNet50 model [ResNet](https://en.wikipedia.org/wiki/Residual_neural_network) is a Residual neural Network structure. It is an innovative neural network created for image classification. The **ResNet** model architecture allows the training error to be reduced with a deeper network through **connection skip**. Residual neural networks ignore some connections and make double or triple layer jumps that contain non-linearities (ReLU). ![image](/images/public-cloud/ai-machine-learning/notebook-tuto-07-transfer-learning-resnet50-image-classification/resnet.png) With this method, performance is generally improved. ResNet has many variants that work on the same concept but have different numbers of layers. **Resnet50** is used to refer to the variant that can work with fifty neural network layers. It was trained on more than a million images from the [ImageNet database](https://www.image-net.org/). ## Requirements - An AI Notebooks project created inside a [Public Cloud project](https://www.ovhcloud.com/it/public-cloud/) in your OVHcloud account - A [user](/it/guides/public-cloud/ai-machine-learning/ai-users.md) for AI Notebooks *** ### OVHcloud Control Panel Access - **Direct link:** Public Cloud Projects - **Navigation path:** Public Cloud > Select your project *** ## Instructions First, you have to create 2 object containers in your OVHcloud **Object Storage**. - The first one contains the non-pre-processed data (base images). - The second object container is empty. It is intended to receive the data once processed and split for training. :::info To know more about how to **push your data to Object Storage**, please refer to the dedicated [documentation](/it/guides/public-cloud/ai-machine-learning/ai-cli-data.md). ::: Then, you can launch your notebook from the OVHcloud Control Panel or via the ovhai [CLI](/it/guides/public-cloud/ai-machine-learning/ai-cli-run-notebook.md) . ### Launching a Jupyter notebook with "Miniconda" via UI 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 `TensorFlow` framework is used. For this tutorial, you can use the following TensorFlow framework version: `tf2.4-py38-cuda11.0-v22-4`. #### Resources You can choose the number of CPUs or GPUs you want. :::info Here, using `1 GPU` is sufficient. ::: #### Attach a Git container or repository 1. Attach the object container (from the Object Storage) that contains your **dataset ** for image classification. - Mount directory: `/workspace/data` - Permission: `read only` (RO) 1. Attach an empty object container to store your **data **, once it has been **processed ** and **split ** for training, validation and test. - Mount directory: `/workspace/data-split` - Permission: `read write` (RW) 1. Attach an empty object container to store your **model ** after training. - Mount directory: `/workspace/saved_model` - Permission: `read write` (RW) :::info To learn more about how to use and **manage your data in a notebook with UI**, check this [documentation](/it/guides/public-cloud/ai-machine-learning/ai-notebooks-manage-data-ui.md). ::: ### Launching a Jupyter notebook with TensorFlow via CLI If you want to launch it with the CLI, choose the `jupyterlab` editor and the `tensorflow` framework. For this tutorial, you can use the following TensorFlow framework version: `tf2.4-py38-cuda11.0-v22-4`. :::info To know more about how to use and **manage your data in a notebook with the CLI**, refer to this [documentation](/it/guides/public-cloud/ai-machine-learning/ai-cli-access-data.md). ::: Choose the number of GPUs (``) to use in your notebook and use the following command. ```console ovhai notebook run tensorflow jupyterlab \ --name \ --framework-version tf2.4-py38-cuda11.0-v22-4 \ --volume @/:/workspace/data:RO:cache \ --volume @/:/workspace/saved_model:RW \ --gpu ``` You can then reach your notebook’s URL once the notebook is running. ### Accessing the notebook Once the repository has been cloned, find your notebook by following this path: `ai-training-examples` > `notebooks` > `computer-vision` > `image-classification` > `tensorflow` > `notebook-resnet-transfer-learning-image-classification.ipynb`. A preview of this notebook can be found on GitHub [here](https://github.com/ovh/ai-training-examples/blob/main/notebooks/computer-vision/image-classification/tensorflow/resnet50/notebook-resnet-transfer-learning-image-classification.ipynb). ## Go further - If you want to deploy a Gradio app for **Image classification** or **Sketch recognition**, check out this [documentation](/it/guides/public-cloud/ai-machine-learning/ai-deploy-gradio-sketch-recognition.md). - If you are interested in **Computer Vision**, familiarise yourself with Object Detection by following this [tutorial](/it/guides/public-cloud/ai-machine-learning/ai-notebooks-yolov5-example.md). If you need training or technical assistance to implement our solutions, contact your sales representative or click on [this link](https://www.ovhcloud.com/it/professional-services/) 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](https://discord.gg/ovhcloud)