--- title: "AI Deploy - Tutorial - Deploy a Gradio app for sketch recognition" description: "Learn how to deploy an application for sketch recognition using a trained model." url: https://docs.us.ovhcloud.com/en/public-cloud/ai-machine-learning/ai-deploy-gradio-sketch-recognition lang: en --- > For AI agents: the complete documentation index is available at https://docs.us.ovhcloud.com/en/llms.txt, the full documentation bundle is available at https://docs.us.ovhcloud.com/en/llms-full.txt. # AI Deploy - Tutorial - Deploy a Gradio app for sketch recognition **Learn how to deploy an application for sketch recognition using a trained model.** **Note:** AI Deploy is covered by **[OVHcloud Public Cloud Special Conditions](https://us.ovhcloud.com/legal/service-specific-terms/)**. The use case is **handwritten digit recognition**, based on the [MNIST dataset](http://yann.lecun.com/exdb/mnist/). To do this, you will use [Gradio](https://gradio.app/), an open-source Python library that is a quick way to expose and use Machine Learning models. You will also learn how to build and use a custom Docker image for a Gradio application. Overview of the app:   ## Requirements - Access to the [OVHcloud Control Panel](https://manager.us.ovhcloud.com/) - An AI Deploy project created inside a [Public Cloud project](https://us.ovhcloud.com/public-cloud/) in your OVHcloud account - A [user for AI Deploy](https://docs.us.ovhcloud.com/en/public-cloud/ai-machine-learning/manage-users-roles.md) - [Docker](https://www.docker.com/get-started) installed on your local computer - Some knowledge about building image and [Dockerfile](https://docs.docker.com/engine/reference/builder/) - You also should have followed the steps of the _Image Classification with MNIST dataset_ notebook from the [GitHub repository](https://github.com/ovh/ai-training-examples/blob/main/notebooks/computer-vision/image-classification/tensorflow/weights-and-biases/notebook_Weights_and_Biases_MNIST.ipynb). You will be able to train and save your model. To launch this notebook and run it, please refer to this [documentation](https://docs.us.ovhcloud.com/en/public-cloud/ai-machine-learning/ai-notebooks-weights-biases.md).   ## Instructions You are going to follow different steps to build your **Gradio** application. - More information about Gradio's capabilities can be found [here](https://gradio.app/docs/). - A direct link to the full Python file can be found [here](https://github.com/ovh/ai-training-examples/blob/main/apps/gradio/sketch-recognition/app.py). Here we will mainly discuss how to write the `app.py` code, the `requirements.txt` file, and the `Dockerfile`. If you want to see the whole code, please refer to the [GitHub repository](https://github.com/ovh/ai-training-examples/tree/main/apps/gradio/sketch-recognition).   ### Write the Gradio application Create a Python file named `app.py`. Inside that file, import your required modules. ```python import gradio as gr import tensorflow as tf import cv2 ``` Define the elements that make up the AI Deploy app: title, header, and references. ```python title = "Welcome on your first sketch recognition app!" head = ( "
" "" "The robot was trained to classify numbers (from 0 to 9). To test it, write your number in the space provided." "
" ) ref = "Find the whole code [here](https://github.com/ovh/ai-training-examples/tree/main/apps/gradio/sketch-recognition)." ``` Specify the input image's size and the class names. ```python img_size = 28 labels = ["zero", "one", "two", "three", "four", "five", "six", "seven", "eight", "nine"] ``` Load the previously trained model for handwritten digits classification. **Note:** To learn more about how you can save a model with TensorFlow, please refer to the part _"Save and export the model for future inference"_ of the [notebook](https://github.com/ovh/ai-training-examples/blob/main/notebooks/computer-vision/image-classification/tensorflow/weights-and-biases/notebook_Weights_and_Biases_MNIST.ipynb). **Note:** Here you will use your trained model, then save it in an Object Storage container. Click [here](https://docs.us.ovhcloud.com/en/public-cloud/ai-machine-learning/cli-data.md) to learn more about Object Storage. ```python model = tf.keras.models.load_model("model/sketch_recognition_numbers_model.h5", compile=False) ``` Create the function that recognizes the written number. ```python def predict(img): img = cv2.resize(img, (img_size, img_size)) img = img.reshape(1, img_size, img_size, 1) preds = model.predict(img)[0] return {label: float(pred) for label, pred in zip(labels, preds)} label = gr.outputs.Label(num_top_classes=3) ``` Launch the Gradio interface. ```python interface = gr.Interface(fn=predict, inputs="sketchpad", outputs=label, title=title, description=head, article=ref) interface.launch(server_name="0.0.0.0", server_port=8080) ```   ### Write the requirements.txt file for the application The `requirements.txt` file will allow us to get all the modules needed to make our application work. This file will be useful when writing the `Dockerfile`. ```console gradio==3.0.10 tensorflow==2.9.1 opencv-python-headless==4.6.0.66 ```   ### Write the Dockerfile for the application Your Dockerfile should start with the `FROM` instruction indicating the parent image to use. In our case we choose to start from the `python:3.7` image: ```console FROM python:3.7 ``` Create the home directory and add your files to it: ```console WORKDIR /workspace ADD . /workspace ``` Install your needed Python modules using a `pip install ...` command with the `requirements.txt` file which contains all modules: ```console RUN pip install -r requirements.txt ``` Give correct access rights to the **ovhcloud user** (`42420:42420`): ```console RUN chown -R 42420:42420 /workspace ENV HOME=/workspace ``` Define your default launching command to start the application: ```console CMD [ "python3" , "/workspace/app.py" ] ```   ### Build the Docker image from the Dockerfile From the directory containing your **Dockerfile**, run one of the following commands to build your application image: ```console # Build the image using your machine's default architecture docker build . -t gradio_app:latest # Build image targeting the linux/amd64 architecture docker buildx build --platform linux/amd64 -t gradio_app:latest . ``` - The **first command** builds the image using your system’s default architecture. This may work if your machine already uses the `linux/amd64` architecture, which is required to run containers with our AI products. However, on systems with a different architecture (e.g. `ARM64` on `Apple Silicon`), the resulting image will not be compatible and cannot be deployed. - The **second command** explicitly targets the `linux/AMD64` architecture to ensure compatibility with our AI services. This requires `buildx`, which is not installed by default. If you haven’t used `buildx` before, you can install it by running: `docker buildx install` **Note:** The dot `.` argument indicates that your build context (place of the **Dockerfile** and other needed files) is the current directory. The `-t` argument allows you to choose the identifier to give to your image. Usually image identifiers are composed of a **name** and a **version tag** `:`. For this example we chose **gradio\_app:latest**.   ### Push the image into the shared registry **Warning:** **NOTE:** The shared registry should only be used for testing purposes. Please consider creating and attaching your own registry. More information about this can be found [here](https://docs.us.ovhcloud.com/en/public-cloud/ai-machine-learning/manage-registries.md). The images pushed to this registry are for AI Tools workloads only, and will not be accessible for external uses. Find the address of your shared registry by launching this command: ```console ovhai registry list ``` Log in on the shared registry with your usual AI Platform user credentials: ```console docker login -u -p ``` Push the created image into the shared registry: ```console docker tag gradio_app:latest /gradio_app:latest docker push /gradio_app:latest ```   ### Launch the AI Deploy app The following command starts a new AI Deploy app running your Gradio application: ```console ovhai app run \ --cpu 1 \ --volume @/model/:/workspace/model:RO \ /gradio_app:latest ``` **Note:** `--cpu 1` indicates that we request 1 CPU for that AI Deploy app. If you want, you can also launch this AI Deploy app with one or more **GPUs**. To launch your Gradio app, you need to attach **1 volume** to this AI Deploy app. It contains the model that you trained before in part _"Save and export the model for future inference"_ of the [notebook](https://github.com/ovh/ai-training-examples/blob/main/notebooks/computer-vision/image-classification/tensorflow/weights-and-biases/notebook_Weights_and_Biases_MNIST.ipynb). **Note:** `--volume @/:/workspace/saved_model:RO` is the volume attached for using your **pretrained model**. This volume is read-only (`RO`) because you just need to use the model and not make any changes to this Object Storage container. If you want your **AI Deploy app** to be accessible without the need to authenticate, specify it as follows. **Note:** Consider adding the `--unsecure-http` attribute if you want your application to be reachable without any authentication.   ## Go further Browse all the [AI & Machine Learning guides](https://docs.us.ovhcloud.com/en/public-cloud/ai-machine-learning/landing-page-ai-machine-learning.md). Browse the rest of the [OVHcloud US documentation](https://docs.us.ovhcloud.com/en/index.md) for guides on our other products and services. Learn more about [AI & Machine Learning](https://us.ovhcloud.com/public-cloud/ai-machine-learning/) on the OVHcloud US website. If you need training or technical assistance to implement our solutions, contact your sales representative or click on [this link](https://us.ovhcloud.com/professional-services/) to get a quote and ask our Professional Services experts for a custom analysis of your project.