DEV Community

Cover image for Build an Image Classification API Using Django Rest Framework.
paulsaul621
paulsaul621

Posted on

Build an Image Classification API Using Django Rest Framework.

#machinelearning #api #django #ai

Overview:

Machine Learning (ML) and data science applications are in high demand. When ML algorithms offer information before it is known, the benefits for business are significant. Integrating machine learning algorithms for inference into production systems is a technological barrier hence the need for deploying ML models as API'S.

Introduction

In this short article, we implement AI based models to detect COVID-19 in Chest X-rays and CT Scans using four Deep Learning Algorithms: VGG16, ResNet50, InceptionV3 and Xception. Note, we shall focus mainly on implementing the api and not the model creation.

To test my live endpoint, send a POST request to the following URL with an x-ray image appended to the body of the request. You will get the following sample output if request was successful:

https://alienx.tech/api/v1/xray # for the x-ray images
https://alienx.tech/api/v1/ct # for CT scans
Enter fullscreen mode Exit fullscreen mode 
{
    "status": "success",
    "data": {
        "asset_id": "3e978ba830fb266978af20f2bf816f5e",
        "public_id": "vacpxfywfohgfprwhrso",
        "version": 1637699139,
        "version_id": "c9017c7d3b28ce797edefec0b0d72796",
        "signature": "e9c632b832e773cbbcb8906f93aba1d9e859d4bf",
        "width": 1205,
        "height": 1395,
        "format": "png",
        "resource_type": "image",
        "created_at": "2021-11-23T20:25:39Z",
        "tags": [],
        "bytes": 1325222,
        "type": "upload",
        "etag": "86005d3c34202b10949db5569570cd16",
        "placeholder": false,
        "url": "http://res.cloudinary.com/prometheusapi/image/upload/v1637699139/vacpxfywfohgfprwhrso.png",
        "secure_url": "https://res.cloudinary.com/prometheusapi/image/upload/v1637699139/vacpxfywfohgfprwhrso.png",
        "original_filename": "covid-19-pneumonia-22",
        "api_key": "138196782467569"
    },
    "url": "http://res.cloudinary.com/prometheusapi/image/upload/v1637699139/vacpxfywfohgfprwhrso.png",
    "xception_chest_pred": "100.00% COVID",
    "inception_chest_pred": "100.00% COVID",
    "vgg_chest_pred": "100.00% COVID",
    "resnet_chest_pred": "100.00% COVID"
}
Enter fullscreen mode Exit fullscreen mode

ML Model Building

The dataset for the project was gathered from two open source Github repositories:

Four algorithms: VGG16, ResNet50, InceptionV3 and Xception were trained separately on Chest X-rays and CT Scans, giving us a total of 8 deep learning models. 80% of the images were used for training the models and the remaining 20% for testing the accuracy of the models.

The code for training the 8 models is available on my github repository. The model for the project can be found on the following google drive.

Turning the Model into an RESTFUL API

Following Python best practices, we will create a virtual environment for our project, and install the required packages.

First, create the project directory.

$ mkdir djangoapp
$ cd djangoapp
Enter fullscreen mode Exit fullscreen mode

Now, create a virtual environment and install the required packages.

For macOS and Unix systems:

$ python3 -m venv myenv
$ source myenv/bin/activate
(myenv) $ pip install django requests djangorestframework tensorflow cloudinary opencv-python
Enter fullscreen mode Exit fullscreen mode

For Windows:

$ python3 -m venv myenv
$ myenv\Scripts\activate
(myenv) $ pip install django requests djangorestframework tensorflow cloudinary opencv-python
Enter fullscreen mode Exit fullscreen mode

Setting Up Your Django Application

First, navigate to the directory djangoapp we created and establish a Django project.

(myenv) $ django-admin startproject mainapp
Enter fullscreen mode Exit fullscreen mode

This will auto-generate some files for your project skeleton:

mainapp/
    manage.py
    mainapp/
        __init__.py
        settings.py
        urls.py
        asgi.py
        wsgi.py
Enter fullscreen mode Exit fullscreen mode

Now, navigate to the directory you just created (make sure you are in the same directory as manage.py) and create your app directory.

(myenv) $ python manage.py startapp monitor
Enter fullscreen mode Exit fullscreen mode

This will create the following:

monitor/
    __init__.py
    admin.py
    apps.py
    migrations/
        __init__.py
    models.py
    tests.py
    views.py
Enter fullscreen mode Exit fullscreen mode

On the mainapp/settings.py file, look for the following line and add the app we just created above.

INSTALLED_APPS = [
    'django.contrib.admin',
    'django.contrib.auth',
    'django.contrib.contenttypes',
    'django.contrib.sessions',
    'django.contrib.messages',
    'django.contrib.staticfiles',
    'rest_framework',#new line
    'monitor', #new line
]
Enter fullscreen mode Exit fullscreen mode

Ensure you are in the monitor directory then create a new directory called templates and a new file called urls.py. Your directory structure of monitor application should look like this

monitor/
    __init__.py
    admin.py
    apps.py
    migrations/
    templates/
        __init__.py
    models.py
    tests.py
    urls.py
    views.py
Enter fullscreen mode Exit fullscreen mode

Ensure your mainapp/urls.py file, add our monitor app URL to include the URLs we shall create next on the monitor app:

from django.contrib import admin
from django.urls import path, include

urlpatterns = [
    #path('admin/', admin.site.urls),
    path('', include('monitor.urls')),#monitor app url
]
Enter fullscreen mode Exit fullscreen mode

Now, on the monitor/urls.py file, add our website there:

from django.urls import path
from .views import *

urlpatterns = [
    path('api/upload/xray', UploadView.as_view(), name = 'prediction'),
    path('api/upload/ct', CTUploadView.as_view(), name = 'ct_prediction'),
]
Enter fullscreen mode Exit fullscreen mode

Let’s create another directory to store our machine learning model. I’ll also add the dataset to the project for those who want to achieve the whole dataset. (It is not compulsory to create a data folder.)

(venv)$ mkdir ml
(venv)$ mkdir ml/models
(venv)$ mkdir ml/data
Enter fullscreen mode Exit fullscreen mode

We also need to tell Django where our machine learning model is located and also add our cloudinary configuration there. Add these lines to settings.py file:

import os
import cloudinary

cloudinary.config( 
  cloud_name = "prometheusapi", 
  api_key = "GETYOURAPIKEY", 
  api_secret = "GETYOURAPIKEY" 
)

MODELS = os.path.join(BASE_DIR, 'ml/models')
Enter fullscreen mode Exit fullscreen mode

Load Keras Model through apps.py

Load your machine learning models in apps.py so that when the application starts, the trained model is loaded only once. Otherwise, the trained model is loaded each time an endpoint is called, and then the response time will be slower.

Let’s update apps.py

import os
from django.apps import AppConfig
from django.conf import settings
from tensorflow.keras.models import load_model
from tensorflow import keras


class ResNetModelConfig(AppConfig):
    name = 'resnetAPI'
    MODEL_FILE = os.path.join(settings.MODELS, "resnet_chest.h5")
    model = keras.models.load_model(MODEL_FILE)

class ResNetCTModelConfig(AppConfig):
    name = 'resnetCTAPI'
    MODEL_FILE = os.path.join(settings.MODELS, "resnet_ct.h5")
    model = keras.models.load_model(MODEL_FILE)

class VGGModelConfig(AppConfig):
    name = 'vggAPI'
    MODEL_FILE = os.path.join(settings.MODELS, "vgg_chest.h5")
    model = keras.models.load_model(MODEL_FILE)

class VGGCTModelConfig(AppConfig):
    name = 'vggCTAPI'
    MODEL_FILE = os.path.join(settings.MODELS, "vgg_ct.h5")
    model = keras.models.load_model(MODEL_FILE)    

class InceptionModelConfig(AppConfig):
    name = 'inceptionv3_chestAPI'
    MODEL_FILE = os.path.join(settings.MODELS, "inceptionv3_chest.h5")    
    model = keras.models.load_model(MODEL_FILE)

class InceptionCTModelConfig(AppConfig):
    name = 'inceptionv3_chestCTAPI'
    MODEL_FILE = os.path.join(settings.MODELS, "inception_ct.h5")    
    model = keras.models.load_model(MODEL_FILE)    

class ExceptionModelConfig(AppConfig):
    name = 'xception_chestAPI'
    MODEL_FILE = os.path.join(settings.MODELS, "xception_chest.h5")    
    model = keras.models.load_model(MODEL_FILE)

class ExceptionCTModelConfig(AppConfig):
    name = 'xception_chestCTAPI'
    MODEL_FILE = os.path.join(settings.MODELS, "xception_ct.h5")    
    model = keras.models.load_model(MODEL_FILE)
Enter fullscreen mode Exit fullscreen mode

Edit views.py

The last step is to update views.py. The views will be mainly responsible for two tasks:

  • Process incoming POST requests.
  • Make a prediction with the incoming data and give the result as a Response. 
import urllib
from django.shortcuts import render
import numpy as np
from .apps import *
from rest_framework.views import APIView
from rest_framework.response import Response
from rest_framework.parsers import MultiPartParser, JSONParser
import cloudinary.uploader
import matplotlib.pyplot as plt
import cv2

# Create your views here.
class UploadView(APIView):
    parser_classes = (
        MultiPartParser,
        JSONParser,
    )

    @staticmethod
    def post(request):
        file = request.data.get('picture')
        upload_data = cloudinary.uploader.upload(file)
        #print(upload_data)
        img = upload_data['url']


        #load models
        resnet_chest = ResNetModelConfig.model
        vgg_chest = VGGModelConfig.model
        inception_chest = InceptionModelConfig.model
        xception_chest = ExceptionModelConfig.model

        req = urllib.request.urlopen(img)
        arr = np.asarray(bytearray(req.read()), dtype=np.uint8)
        image = cv2.imdecode(arr, -1) # 'Load it as it is'
        #image = cv2.imread('upload_chest.jpg') # read file 
        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) # arrange format as per keras
        image = cv2.resize(image,(224,224))
        image = np.array(image) / 255
        image = np.expand_dims(image, axis=0)

        resnet_pred = resnet_chest.predict(image)
        probability = resnet_pred[0]
        #print("Resnet Predictions:")
        if probability[0] > 0.5:
            resnet_chest_pred = str('%.2f' % (probability[0]*100) + '% COVID') 
        else:
            resnet_chest_pred = str('%.2f' % ((1-probability[0])*100) + '% NonCOVID')
        #print(resnet_chest_pred)

        vgg_pred = vgg_chest.predict(image)
        probability = vgg_pred[0]
        #print("VGG Predictions:")
        if probability[0] > 0.5:
            vgg_chest_pred = str('%.2f' % (probability[0]*100) + '% COVID') 
        else:
            vgg_chest_pred = str('%.2f' % ((1-probability[0])*100) + '% NonCOVID')
        #print(vgg_chest_pred)

        inception_pred = inception_chest.predict(image)
        probability = inception_pred[0]
        #print("Inception Predictions:")
        if probability[0] > 0.5:
            inception_chest_pred = str('%.2f' % (probability[0]*100) + '% COVID') 
        else:
            inception_chest_pred = str('%.2f' % ((1-probability[0])*100) + '% NonCOVID')
        #print(inception_chest_pred)

        xception_pred = xception_chest.predict(image)
        probability = xception_pred[0]
        #print("Xception Predictions:")
        if probability[0] > 0.5:
            xception_chest_pred = str('%.2f' % (probability[0]*100) + '% COVID') 
        else:
            xception_chest_pred = str('%.2f' % ((1-probability[0])*100) + '% NonCOVID')
        #print(xception_chest_pred)
        return Response({
            'status': 'success',
            'data': upload_data,
            'url':img,
            'xception_chest_pred':xception_chest_pred,
            'inception_chest_pred':inception_chest_pred,
            'vgg_chest_pred':vgg_chest_pred,
            'resnet_chest_pred':resnet_chest_pred,
        }, status=201)


class CTUploadView(APIView):
    parser_classes = (
        MultiPartParser,
        JSONParser,
    )

    @staticmethod
    def post(request):
        file = request.data.get('picture')
        upload_data = cloudinary.uploader.upload(file)
        #print(upload_data)
        img = upload_data['url']


        #load models
        resnet_chest = ResNetCTModelConfig.model
        vgg_chest = VGGCTModelConfig.model
        inception_chest = InceptionCTModelConfig.model
        xception_chest = ExceptionCTModelConfig.model

        req = urllib.request.urlopen(img)
        arr = np.asarray(bytearray(req.read()), dtype=np.uint8)
        image = cv2.imdecode(arr, -1) # 'Load it as it is'
        #image = cv2.imread('upload_chest.jpg') # read file 
        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) # arrange format as per keras
        image = cv2.resize(image,(224,224))
        image = np.array(image) / 255
        image = np.expand_dims(image, axis=0)

        resnet_pred = resnet_chest.predict(image)
        probability = resnet_pred[0]
        #print("Resnet Predictions:")
        if probability[0] > 0.5:
            resnet_chest_pred = str('%.2f' % (probability[0]*100) + '% COVID') 
        else:
            resnet_chest_pred = str('%.2f' % ((1-probability[0])*100) + '% NonCOVID')
        #print(resnet_chest_pred)

        vgg_pred = vgg_chest.predict(image)
        probability = vgg_pred[0]
        #print("VGG Predictions:")
        if probability[0] > 0.5:
            vgg_chest_pred = str('%.2f' % (probability[0]*100) + '% COVID') 
        else:
            vgg_chest_pred = str('%.2f' % ((1-probability[0])*100) + '% NonCOVID')
        #print(vgg_chest_pred)

        inception_pred = inception_chest.predict(image)
        probability = inception_pred[0]
        #print("Inception Predictions:")
        if probability[0] > 0.5:
            inception_chest_pred = str('%.2f' % (probability[0]*100) + '% COVID') 
        else:
            inception_chest_pred = str('%.2f' % ((1-probability[0])*100) + '% NonCOVID')
        #print(inception_chest_pred)

        xception_pred = xception_chest.predict(image)
        probability = xception_pred[0]
        #print("Xception Predictions:")
        if probability[0] > 0.5:
            xception_chest_pred = str('%.2f' % (probability[0]*100) + '% COVID') 
        else:
            xception_chest_pred = str('%.2f' % ((1-probability[0])*100) + '% NonCOVID')
        #print(xception_chest_pred)
        return Response({
            'status': 'success',
            'data': upload_data,
            'url':img,
            'xceptionCT_chest_pred':xception_chest_pred,
            'inceptionCT_chest_pred':inception_chest_pred,
            'vggCT_chest_pred':vgg_chest_pred,
            'resnetCT_chest_pred':resnet_chest_pred,
        }, status=201)
Enter fullscreen mode Exit fullscreen mode

Testing our API

Create the necessary migrations then run the server:

(myenv) $ python manage.py makemigrations
(myenv) $ python manage.py migrate
(myenv) $ python manage.py runserver
Enter fullscreen mode Exit fullscreen mode

Fire up Postman and make a POST request with an image appended to the body.

polo.png

Thanks for staying tuned!

Top comments (6)

Collapse
 
raaphat99 profile image
Ahmed Raaphat • • Edited

I followed the exact same steps and got this error when testing the api. "Error at /api/upload/xray"
I can't test the live endpoints, too. Because the pages no longer exist.
Any help?

Collapse
 
paulwababu profile image
paulsaul621 •

Hello, sadly i took down that api so it is not available

Collapse
 
raaphat99 profile image
Ahmed Raaphat •

So could you post it and make it available again? I don't mind purchasing the hosting fees if that works for you.

Thread Thread
 
paulwababu profile image
paulsaul621 •

you need a project? I can give you the source code..

Thread Thread
 
raaphat99 profile image
Ahmed Raaphat •

I need the API for an academic project that I am working on. But well, I am sending you an email.

Thread Thread
 
paulwababu profile image
paulsaul621 •

ok, let me reply now, just seen your email

Read next

dumebii profile image

API Documentation Tools: Using Hoppscotch for API Documentation

Dumebi Okolo -

satya_prakash profile image

A Beginner’s Guide to Component Testing with Playwright

satyaprakash behera -

thisweekinjavascript profile image

Claude AI now runs JavaScript, Python beats JavaScript on GitHub, new Node.js versions and more

James -

muash10 profile image

Using Stable Diffusion in AWS Bedrock to Generate Images

Muhammed Ashraf -