AI Deploy - Tutorial - Create a web service to recognize sign language with YOLOv7

Objective

The purpose of this tutorial is to show how to deploy a web service to recognize American Sign Language letters using YOLOv7 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.

For more information on how to train YOLOv7 on a custom dataset, refer to the following documentation.

Here is an overview of the Sign Language recognition app:

Requirements

• An AI Deploy project created inside a Public Cloud project
• A user for AI Deploy
• Docker installed on your local computer
• Some knowledge about building image and Dockerfile
• Your weights obtained from training YOLOv7 model on the ASL letters dataset (refer to the "Export trained weights for future inference" part of the notebook for YOLOv7

Instructions

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

• More information about Streamlit capabilities can be found here.
• Direct link to the full Python script can be found here.

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

Write the Streamlit application

Create a Python file named main.py.

Inside that file, import your required modules:

import streamlit as st
from PIL import Image
import numpy as np
import torch
import cv2
import io
import os

Load the YOLOv7 model and your own weights. Put this function in cache:

@st.cache
def load_model():

    custom_yolov7_model = torch.hub.load("WongKinYiu/yolov7", 'custom', '/workspace/asl-volov7-model/yolov7.pt')

    return custom_yolov7_model

Create the inference function to get prediction:

def get_prediction(img_bytes, model):

    img = Image.open(io.BytesIO(img_bytes))
    results = model(img, size=640)

    return results

Write the image analysis function:

def analyse_image(image, model):

    if image is not None:

        img = Image.open(image)
        bytes_data = image.getvalue()
        img_bytes = np.asarray(bytearray(bytes_data), dtype=np.uint8)
        result = get_prediction(img_bytes, model)
        result.render()

        for img in result.imgs:
            RGB_img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
            im_arr = cv2.imencode('.jpg', RGB_img)[1]
            st.image(im_arr.tobytes())

        result_list = list((result.pandas().xyxy[0])["name"])

    else:
        st.write("no asl letters were detected!")
        result_list = []

    return result_list

Define the Python function that displays the letters and forms a word:

def display_letters(letters_list):

    word = ''.join(letters_list)
    path_file = "/workspace/word_file.txt"
    with open(path_file, "a") as f:
        f.write(word)

    return path_file

Define the main and start your app:

if __name__ == '__main__':

    st.image("/workspace/head-asl-yolov7-app.png")
    st.write("## Welcome on your ASL letters recognition app!")

    model = load_model()

    img_file_buffer = st.camera_input("Take your picture in real time:")

    result_list = analyse_image(img_file_buffer, model)
    path_file = display_letters(result_list)

    if st.button("Clear result"):
        if os.path.isfile(path_file):
            os.remove(path_file)
            print("File has been deleted")
        else:
            print("File does not exist")

    if (os.path.exists(path_file)==True):
        with open(path_file, "r") as f:
            content = f.read()
            st.write(content)
            f.close()
    else:
        pass

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.

torchvision==0.14.0
numpy==1.23.4
pandas==1.5.1
matplotlib==3.6.2
pillow==9.3.0
opencv-python-headless==4.6.0.66
streamlit==1.14.0
tqdm==4.64.1
seaborn==0.12.1
scipy==1.9.3
ipython==8.6.0
psutil==5.9.4
pyyaml==6.0

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:

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 [ "streamlit" , "run" , "/workspace/main.py", "--server.address=0.0.0.0" ]

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

From the directory containing your Dockerfile, run one of the following commands to build your application image:

# Build the image using your machine's default architecture
docker build . -t yolov7-streamlit-asl-recognition:latest

# Build image targeting the linux/amd64 architecture
docker buildx build --platform linux/amd64 -t yolov7-streamlit-asl-recognition: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

Test it locally (optional)

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

docker run --rm -it -p 8501:8051 --user=42420:42420 yolov7-streamlit-asl-recognition:latest

Once started, your application should be available on http://localhost:8501.

Push the image into the shared registry

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 tag yolov7-streamlit-asl-recognition:latest <shared-registry-address>/yolov7-streamlit-asl-recognition:latest
docker push <shared-registry-address>/yolov7-streamlit-asl-recognition:latest

Launch the AI Deploy app

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

ovhai app run <shared-registry-address>/yolov7-streamlit-asl-recognition:latest \
       --gpu 1 \
       --default-http-port 8501 \
       --volume asl-volov7-model@GRA/:/workspace/asl-volov7-model:RO

Go further

• You can imagine deploying an app using YOLO models with another Python framework: Flask. Refer to this tutorial.
• Feel free to use Streamlit for other AI tasks! Deploy a Speech-to-Text app here.

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.