Skip to content
Related Articles

Related Articles

Improve Article
Exposing ML/DL Models as REST APIs
  • Difficulty Level : Medium
  • Last Updated : 17 Jan, 2019

In this article, we will learn how to expose ML/DL model as flask APIs.

Frameworks we’ll be using:
Keras is a Deep Learning library, built on top of backends such as Tensorflow, Theano or CNTK. It provides abstraction and allows rapid development of ML/DL models.

Flask is a micro web framework in Python, which is used to quickly spin up servers to serve pages. Refer Introduction to Flask.

Since the focus of the article is to serve a ML/DL model using an API, we wouldn’t get deeper into the making of the Convolutional model. We will be using the ResNet50 Convolutional Neural Network.

Install Tensorflow and Keras

Update pippip install -U pippython -m pip install -U pip
Install virtualenvsudo pip install virtualenvpip install virtualenv
Create a new folder ml-apimkdir ml-api && cd ml-apimkdir ml-api && cd ml-apiCreate a virtual environment(Good practice) and activate itvirtualenv –system-site-packages -p python3 ./venvvirtualenv –system-site-packages -p python3 ./venvActivate the virtual environmentsource ./venv/bin/activate

.\venv\Scripts\activateInstall TensorFlowpip install –upgrade tensorflowpip install –upgrade tensorflowInstall Keraspip install keraspip install kerasInstall other dependenciespip install flask gevent requests pillowpip install flask gevent requests pillow


Creating the REST API :

# Python program to expose a ML model as flask REST API
# import the necessary modules
from keras.applications import ResNet50 # pre-built CNN Model
from keras.preprocessing.image import img_to_array 
from keras.applications import imagenet_utils
import tensorflow as tf
from PIL import Image
import numpy as np
import flask
import io
# Create Flask application and initialize Keras model
app = flask.Flask(__name__)
model = None
# Function to Load the model 
def load_model():
    # global variables, to be used in another function
    global model     
    model = ResNet50(weights ="imagenet")
    global graph 
    graph = tf.get_default_graph()
# Every ML/DL model has a specific format
# of taking input. Before we can predict on
# the input image, we first need to preprocess it.
def prepare_image(image, target):
    if image.mode != "RGB":
        image = image.convert("RGB")
    # Resize the image to the target dimensions
    image = image.resize(target) 
    # PIL Image to Numpy array
    image = img_to_array(image) 
    # Expand the shape of an array,
    # as required by the Model
    image = np.expand_dims(image, axis = 0
    # preprocess_input function is meant to
    # adequate your image to the format the model requires
    image = imagenet_utils.preprocess_input(image) 
    # return the processed image
    return image
# Now, we can predict the results.
@app.route("/predict", methods =["POST"])
def predict():
    data = {} # dictionary to store result
    data["success"] = False
    # Check if image was properly sent to our endpoint
    if flask.request.method == "POST":
        if flask.request.files.get("image"):
            image = flask.request.files["image"].read()
            image =
            # Resize it to 224x224 pixels 
            # (required input dimensions for ResNet)
            image = prepare_image(image, target =(224, 224))
        # Predict ! global preds, results
            with graph.as_default():
                preds = model.predict(image)
                results = imagenet_utils.decode_predictions(preds)
                data["predictions"] = []
            for (ID, label, probability) in results[0]:
                r = {"label": label, "probability": float(probability)}
            data["success"] = True
    # return JSON response
    return flask.jsonify(data)
if __name__ == "__main__":
    print(("* Loading Keras model and Flask starting server..."
        "please wait until server has fully started"))

Run the flask server


Note #1: For the first time you run it, it takes time to download the weights of the model. In subsequent runs, this won’t be the case.
Note #2: Save images in the same directory (ml-api) – dog.jpg, cat.jpg, lion.jpg .

Make requests to the server:

Method #1 : use cURL (Download cURL for Windows from here.)

$ curl -X POST -F image=@dog.jpg "http://localhost:5000/predict"

Method #2 : (Suitable if making a Full-stack web app with proper UI)
Create a simple HTML form

<!-- index.html -->
<form action = "http://localhost:5000/predict" method = "POST" 
         enctype = "multipart/form-data">
         <input type = "file" name = "image" />
         <input type = "submit"/>

Method #3 : Create a simple python script to make HTTP requests to flask server.

import requests
import sys
# provide image name as command line argument
IMAGE_PATH = sys.argv[1
image = open(IMAGE_PATH, "rb").read()
payload = {"image": image}
# make request to the API
request =, files = payload).json()
if request["success"]:
    # Print formatted Result
    print("% s % 15s % s"%("Rank", "Label", "Probability"))
    for (i, result) in enumerate(request["predictions"]):
        print("% d.    % 17s %.4f"%(i + 1, result["label"],
        print("Request failed")

Run it as :

python dog.jpg


To deactivate after you are done(both Windows and Linux) :

> deactivate

So the workflow, in general for any model is

  • Build the model and save it.
  • Create a Flask app.
  • Load the Model
  • Define endpoints of API for each type of requests.
  • Preprocess input according to the Model’s architecture and feed it to the model
  • Process the input and send back the output to client.


My Personal Notes arrow_drop_up
Recommended Articles
Page :