TensorFlow Linear Regression Model Access with Custom REST API using Flask

sandbox.py

import numpy as np
import tensorflow as tf
from flask import Flask, jsonify, request
from flask_cors import CORS, cross_origin

app = Flask(__name__)
CORS(app)

@app.route("/redsam/api/v0.1/points", methods=['GET', 'POST'])
def linear_regression_train():
    # CUSTOMIZABLE: Collect/Prepare data
    steps = 100
    learn_rate = 0.0001
    
    if request.method == 'POST':
        steps = request.json['steps']
        learn_rate = request.json['learnrate']
    
    # Model linear regression y = Wx + b
    x = tf.placeholder(tf.float32, [None, 1])
    W = tf.Variable(tf.zeros([1,1]))
    b = tf.Variable(tf.zeros([1]))
    product = tf.matmul(x,W)
    y = product + b
    y_ = tf.placeholder(tf.float32, [None, 1])

    # Cost function sum((y_-y)**2)
    cost = tf.reduce_mean(tf.square(y_-y))

    # Training using Gradient Descent to minimize cost
    train_step = tf.train.GradientDescentOptimizer(learn_rate).minimize(cost)
    
    sess = tf.Session()
    init = tf.initialize_all_variables()
    sess.run(init)
    
    all_points = [];
    eq_vals = [];
    
    for i in range(steps):
        # Create fake data for y = W.x + b where W = 2, b = 0
        xs = np.array([[i]])
        ys = np.array([[2*i]])
        # Train
        feed = { x: xs, y_: ys }
        sess.run(train_step, feed_dict=feed)
              
        all_points.append({"x": xs[0][0], "y": ys[0][0]});

        # NOTE: W should be close to 2, and b should be close to 0 
    
    eq_vals.append({'w': str(sess.run(W)[0][0]), "b": str(sess.run(b)[0]), 
                    "cost": '{0:f}'.format(sess.run(cost, feed_dict=feed))});
    
    response = jsonify(results=[eq_vals, all_points])
    return response

if __name__ == "__main__":
    app.run(host='0.0.0.0')