vrjkmr

# Import libraries
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import tensorflow as tf
from tensorflow.python.framework import ops
from tensorflow.examples.tutorials.mnist import input_data

# Import Fashion MNIST
fashion_mnist = input_data.read_data_sets('input/data', one_hot=True)

vrjkmr

# Shapes of training set
print("Training set (images) shape: {shape}".format(shape=fashion_mnist.train.images.shape))
print("Training set (labels) shape: {shape}".format(shape=fashion_mnist.train.labels.shape))

# Shapes of test set
print("Test set (images) shape: {shape}".format(shape=fashion_mnist.test.images.shape))
print("Test set (labels) shape: {shape}".format(shape=fashion_mnist.test.labels.shape))

'''
Output:

vrjkmr

# Create dictionary of target classes
label_dict = {
 0: ‘T-shirt/top’,
 1: ‘Trouser’,
 2: ‘Pullover’,
 3: ‘Dress’,
 4: ‘Coat’,
 5: ‘Sandal’,
 6: ‘Shirt’,
 7: ‘Sneaker’,

vrjkmr

# Sample 1

# Get 28x28 image
sample_1 = fashion_mnist.train.images[47].reshape(28,28)
# Get corresponding integer label from one-hot encoded data
sample_label_1 = np.where(fashion_mnist.train.labels[47] == 1)[0][0]
# Plot sample
print("y = {label_index} ({label})".format(label_index=sample_label_1, label=label_dict[sample_label_1]))
plt.imshow(sample_1, cmap='Greys')

vrjkmr

# Network parameters
n_hidden_1 = 128 # Units in first hidden layer
n_hidden_2 = 128 # Units in second hidden layer
n_input = 784 # Fashion MNIST data input (img shape: 28*28)
n_classes = 10 # Fashion MNIST total classes (0–9 digits)
n_samples = fashion_mnist.train.num_examples # Number of examples in training set 

vrjkmr

# Create placeholders
def create_placeholders(n_x, n_y):
 '''
 Creates the placeholders for the tensorflow session.
 
 Arguments:
 n_x -- scalar, size of an image vector (28*28 = 784)
 n_y -- scalar, number of classes (10)
 
 Returns:

vrjkmr

def initialize_parameters():
    '''
    Initializes parameters to build a neural network with tensorflow. The shapes are:
                        W1 : [n_hidden_1, n_input]
                        b1 : [n_hidden_1, 1]
                        W2 : [n_hidden_2, n_hidden_1]
                        b2 : [n_hidden_2, 1]
                        W3 : [n_classes, n_hidden_2]
                        b3 : [n_classes, 1]
    

vrjkmr

def forward_propagation(X, parameters):
    '''
    Implements the forward propagation for the model: 
    LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SOFTMAX
    
    Arguments:
    X -- input dataset placeholder, of shape (input size, number of examples)
    parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3"
                  the shapes are given in initialize_parameters
    Returns:

vrjkmr

def compute_cost(Z3, Y):
    '''
    Computes the cost
    
    Arguments:
    Z3 -- output of forward propagation (output of the last LINEAR unit), of shape (10, number_of_examples)
    Y -- "true" labels vector placeholder, same shape as Z3
    
    Returns:
    cost - Tensor of the cost function

vrjkmr

def model(train, test, learning_rate=0.0001, num_epochs=16, minibatch_size=32, print_cost=True, graph_filename='costs'):
    '''
    Implements a three-layer tensorflow neural network: LINEAR->RELU->LINEAR->RELU->LINEAR->SOFTMAX.
    
    Arguments:
    train -- training set
    test -- test set
    learning_rate -- learning rate of the optimization
    num_epochs -- number of epochs of the optimization loop
    minibatch_size -- size of a minibatch