K-Nearest Neighbors with the MNIST Dataset

digitsocr.py

import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
import matplotlib.image as mp_image
import matplotlib.pyplot as mp_pyplot

mnist = input_data.read_data_sets("minst_data/", one_hot=True)
training_digits, training_lables = mnist.train.next_batch(5000)
test_digits, test_lables = mnist.train.next_batch(10)

training_digits_pl = tf.placeholder("float", [None, 784])
test_digit_pl = tf.placeholder("float", [784])

l1_distance = tf.abs(tf.add(training_digits_pl, tf.negative(test_digit_pl)))

distance = tf.reduce_sum(l1_distance, axis=1)

pred = tf.arg_min(distance, 0)

accuracy = 0
init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    for i in range(len(test_digits)):
        pixels = test_digits[i].reshape((28, 28))
        mp_pyplot.imshow(pixels, cmap='gray')
        mp_pyplot.show()
        

        nn_index = sess.run(pred, feed_dict={
            training_digits_pl: training_digits,
            test_digit_pl: test_digits[i, :]
        })
        match = True
        if np.argmax(training_lables[nn_index]) != np.argmax(test_lables[i]):
            match = False

        print("match:", match,"\t",  "prediction:", np.argmax(
            training_lables[nn_index]), "true lable", np.argmax(test_lables[i]))