AI Deploy - Tutorial - Deploy a web service for YOLOv5 using Flask

How to deploy a web service for YOLOv5 using your own weights with Flask

Last updated 31st January, 2023.

AI Deploy is in beta. During the beta-testing phase, the infrastructure’s availability and data longevity are not guaranteed. Please do not use this service for applications that are in production, as this phase is not complete.

AI Deploy is covered by OVHcloud Public Cloud Special Conditions.


The purpose of this tutorial is to show how to deploy a web service for YOLOv5 using your own weights generated after training a YOLOv5 model on your dataset.

In order to do this, you will use Flask, an open-source micro framework for web development in Python. You will also learn how to build and use a custom Docker image for a Flask application.

For more information on how to train YOLOv5 on a custom dataset, refer to the following documentation.



First, the tree structure of your folder should be as follows.


  • You have to create the folder named models_train and this is where you can store the weights generated after your trainings. You are free to put as many weight files as you want in the models_train folder.

  • Here we will mainly discuss how to write the code, the requirements.txt file and the Dockerfile. If you want to see the whole code, please refer to the GitHub repository.

Write the Flask application

Create a Python file named

Inside that file, import your required modules:

import sys
import io
from PIL import Image
import cv2
import torch
from flask import Flask, render_template, request, make_response
from werkzeug.exceptions import BadRequest
import os

Create Flask app:

app = Flask(__name__)

Load your own weights:

Here a python dictionary is created to store the name of each of your weight files (key) and the corresponding model (value).

# create a python dictionary for your models d = {<key>: <value>, <key>: <value>, ..., <key>: <value>}
dictOfModels = {}
# create a list of keys to use them in the select part of the html code
listOfKeys = []

Write the inference function:

def get_prediction(img_bytes,model):
    img =
    # inference
    results = model(img, size=640)  
    return results

Define the GET method:

@app.route('/', methods=['GET'])
def get():
  # in the select we will have each key of the list in option
  return render_template("index.html", len = len(listOfKeys), listOfKeys = listOfKeys)

Define the POST method:

@app.route('/', methods=['POST'])
def predict():
    file = extract_img(request)
    img_bytes =
    # choice of the model
    results = get_prediction(img_bytes,dictOfModels[request.form.get("model_choice")])
    print(f'User selected model : {request.form.get("model_choice")}')
    # updates results.imgs with boxes and labels
    # encoding the resulting image and return it
    for img in results.ims:
        RGB_img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
        im_arr = cv2.imencode('.jpg', RGB_img)[1]
        response = make_response(im_arr.tobytes())
        response.headers['Content-Type'] = 'image/jpeg'
    return response

def extract_img(request):
    # checking if image uploaded is valid
    if 'file' not in request.files:
        raise BadRequest("Missing file parameter!")
    file = request.files['file']
    if file.filename == '':
        raise BadRequest("Given file is invalid")
    return file

Define the main and start your app:

if __name__ == '__main__':

    print('Starting yolov5 webservice...')
    # Getting directory containing models from command args (or default 'models_train')
    models_directory = 'models_train'
    if len(sys.argv) > 1:
        models_directory = sys.argv[1]
    print(f'Watching for yolov5 models under {models_directory}...')
    for r, d, f in os.walk(models_directory):
        for file in f:
            if ".pt" in file:
                # example: file = ""
                # the path of each model: os.path.join(r, file)
                model_name = os.path.splitext(file)[0]
                model_path = os.path.join(r, file)
                print(f'Loading model {model_path} with path {model_path}...')
                dictOfModels[model_name] = torch.hub.load('ultralytics/yolov5', 'custom', path=model_path, force_reload=True)
                # you would obtain: dictOfModels = {"model1" : model1 , etc}
        for key in dictOfModels :
            listOfKeys.append(key) # put all the keys in the listOfKeys

    # starting app,host='')

Find more information about the Flask application here to get ready to use it.

Write the requirements.txt file for the application

The requirements.txt file will allow us to write all the modules needed to make our application work. This file will be useful when writing the Dockerfile.


Write the Dockerfile for the application

Your Dockerfile should start with the the FROM instruction indicating the parent image to use. In our case we choose to start from a python:3.8 image:

FROM python:3.8

Create the home directory and add your files to it:

WORKDIR /workspace
ADD . /workspace

Install the requirements.txt file which contains your needed Python modules using a pip install ... command:

RUN pip install -r requirements.txt

Define your default launching command to start the application:

CMD [ "python" , "/workspace/" ]

Give correct access rights to ovhcloud user (42420:42420):

RUN chown -R 42420:42420 /workspace
ENV HOME=/workspace

Build the Docker image from the Dockerfile

Launch the following command from the Dockerfile directory to build your application image:

docker build . -t flask-yolov5:latest

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 <name>:<version>. For this example we chose flask-yolov5:latest.

Please make sure that the docker image you will push in order to run containers using AI products respects the linux/AMD64 target architecture. You could, for instance, build your image using buildx as follows:

docker buildx build --platform linux/amd64 ...

Test it locally (optional)

Launch the following Docker command to launch your application locally on your computer:

docker run --rm -it -p 5000:5000 --user=42420:42420 flask-yolov5:latest

The -p 5000:5000 argument indicates that you want to execute a port redirection from the port 5000 of your local machine into the port 5000 of the Docker container. The port 5000 is the default port used by Flask applications.

Don't forget the --user=42420:42420 argument if you want to simulate the exact same behaviour that will occur on AI Deploy apps. It executes the Docker container as the specific OVHcloud user (user 42420:42420).

Once started, your application should be available on http://localhost:5000.

Push the image into the shared registry

The shared registry of AI Deploy should only be used for testing purpose. Please consider attaching your own Docker registry. More information about this can be found here.

Find the adress of your shared registry by launching this command:

ovhai registry list

Login on the shared registry with your usual openstack credentials:

docker login -u <user> -p <password> <shared-registry-address>

Push the compiled image into the shared registry:

docker tag flask-yolov5:latest <shared-registry-address>/flask-yolov5:latest
docker push <shared-registry-address>/flask-yolov5:latest

Launch the AI Deploy app

The following command starts a new app running your Flask application:

ovhai app run --default-http-port 5000 --cpu 4 <shared-registry-address>/flask-yolov5:latest

--default-http-port 5000 indicates that the port to reach on the app URL is the 5000.

--cpu 4 indicates that we request 4 CPUs for that app.

Consider adding the --unsecure-http attribute if you want your application to be reachable without any authentication.

Go further

  • You can imagine deploying a Flask app in order to to classify the feelings in a text. Refer to this tutorial.
  • Another way to create an AI Deploy app is to use Streamlit! Here it is.


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

Esta documentação foi-lhe útil?

Não hesite em propor-nos sugestões de melhoria para fazer evoluir este manual.

Imagens, conteúdo, estrutura... Não hesite em dizer-nos porquê para evoluirmos em conjunto!

Os seus pedidos de assistência não serão tratados através deste formulário. Para isso, utilize o formulário "Criar um ticket" .

Obrigado. A sua mensagem foi recebida com sucesso.

Estes manuais também podem ser úteis...

OVHcloud Community

Aceda ao seu espaço comunitário. Coloque as suas questões, procure informações e interaja com outros membros do OVHcloud Community.

Discuss with the OVHcloud community

Em conformidade com a alteração à Diretiva 2006/112/CE, os preços com IVA podem variar de acordo com o país de residência do cliente
(por defeito, os preços com IVA apresentados incluem o IVA português em vigor).