AI Deploy - Tutorial - Create an application to play rock paper scissors with YoloV8

Knowledge Base

KB0069134

AI Deploy - Tutorial - Create an application to play rock paper scissors with YoloV8


Icons/System/eye-open Created with Sketch. 79 Views 27.06.2025 AI Deploy

Objective

The purpose of this tutorial is to explain how to deploy an application to play the game "rock paper scissors" using the YOLOv8 model.

In order to do this, you will use Streamlit, a Python framework that turns scripts into a shareable web application. You will also learn how to build and use a custom Docker image for a Streamlit application.

Requirements

Instructions

You are going to follow different steps to build your Streamlit application.

  • More information about Streamlit capabilities can be found here.
  • All source files can be found on GitHub.

Write the Streamlit application

Create a Python file named app.py and paste the following code:

from ultralytics import YOLO
import streamlit as st

#######################################################################################################################
## 🎯 The aim of this script is to create an Rock/Paper/Scissors application based on a trained model (from YOLOv8). ##
## 🏞 The uploaded snapshots are stored in /workspace/                                                               ##
## 🧠 The train model is stored in /workspace/model/rock-paper-scissors/                                             ##
#######################################################################################################################

# Save uploaded photo
def save_photo(photo):

    photoAbsolutePath = '/workspace/' + photo.name

    with open(photoAbsolutePath,'wb') as f:
         f.write(photo.getbuffer())

    return photoAbsolutePath

# main
if __name__ == '__main__':

    st.write("## Welcome on the 🪨 📄 ✂️ game!")
    # 🧠 Load the model
    model = YOLO('/workspace/model/rock-paper-scissors/best.torchscript')

    # 📸 Camera input
    img_file_buffer = st.camera_input("Take your picture in real time:")
    if img_file_buffer is not None:
      photoPath = save_photo(img_file_buffer) 

      # 🔎 Prediction
      results = model.predict(photoPath, verbose=True, save=True, conf=0.5)

      # 📈 Display results
      for r in results:
        for c in r.boxes.cls:
          st.write(r.names[int(c)])

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.

ultralytics==8.0.194 
opencv-python-headless==4.8.1.78 
streamlit==1.27.2

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 a python:3.8 image:

# 🐳 Base image to execute Python application
FROM python:3.8

# 👱 Userspace for AI Deploy
WORKDIR /workspace
# 📚 Libraries for the application
ADD requirements.txt /workspace
RUN pip install -r requirements.txt
RUN apt-get update
RUN apt-get install ffmpeg libsm6 libxext6  -y

# 🐍 Python application
ADD app.py /workspace

# 👮 Rootless execution
RUN chown -R 42420:42420 /workspace

# 🚀 Run the Python application
CMD [ "streamlit" , "run" , "/workspace/app.py", "--server.address=0.0.0.0" ]

ENV HOME=/workspace

Build the Docker image from the Dockerfile

Launch one of the following commands from the Dockerfile directory to build your application image:

# Build the image using your machine's default architecture
docker build . -f Dockerfile -t <shared-regristry-name>/rock-paper-scissors-app:1.0.0

# Build image targeting the linux/amd64 architecture
docker buildx build --platform linux/amd64 -f Dockerfile -t <shared-regristry-name>/rock-paper-scissors-app:1.0.0 .

  • 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

Push the image into the shared registry

Warning 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. 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:

ovhai registry list

Log in to the shared registry with your usual AI Platform user credentials:

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

Push the compiled image into the shared registry:

docker push <shared-registry-address>/rock-paper-scissors-app:1.0.0

Launch the AI Deploy app

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

ovhai app run \
    --name rock-paper-scissors-app \
    --cpu 1 \
    --default-http-port 8501 \
    --volume rock-paper-scissors-model@GRA:/workspace/model:RO:cache \
    --unsecure-http \
    <shared-registry-address>/rock-paper-scissors-app:1.0.0

Notes

  • --default-http-port 8501 indicates that the port to reach on the app URL is 8501.

  • --cpu 1 indicates that we request only one CPU for that app.

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

Go further

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: