Credits: Forked from deep-learning-keras-tensorflow by Valerio Maggio

# A simple implementation of ANN for MNIST¶

This code was taken from: https://github.com/mnielsen/neural-networks-and-deep-learning

This accompanies the online text http://neuralnetworksanddeeplearning.com/ . The book is highly recommended.

In [1]:
# Import libraries
import random
import numpy as np
import keras
from keras.datasets import mnist

Using Theano backend.
Using gpu device 0: GeForce GTX 760 (CNMeM is enabled with initial size: 90.0% of memory, cuDNN 4007)

In [2]:
# Set the full path to mnist.pkl.gz
# Point this to the data folder inside the repository
path_to_dataset = "euroscipy2016_dl-tutorial/data/mnist.pkl.gz"

In [3]:
!mkdir -p \$HOME/.keras/datasets/euroscipy2016_dl-tutorial/data/

In [4]:
# Load the datasets
(X_train, y_train), (X_test, y_test) = mnist.load_data(path_to_dataset)

Downloading data from https://s3.amazonaws.com/img-datasets/mnist.pkl.gz
15286272/15296311 [============================>.] - ETA: 0s
In [5]:
print(X_train.shape, y_train.shape)
print(X_test.shape, y_test.shape)

(60000, 28, 28) (60000,)
(10000, 28, 28) (10000,)

In [6]:
"""
network.py
~~~~~~~~~~
A module to implement the stochastic gradient descent learning
algorithm for a feedforward neural network.  Gradients are calculated
using backpropagation.  Note that I have focused on making the code
simple, easily readable, and easily modifiable.  It is not optimized,
and omits many desirable features.
"""

#### Libraries
# Standard library
import random

# Third-party libraries
import numpy as np

class Network(object):

def __init__(self, sizes):
"""The list sizes contains the number of neurons in the
respective layers of the network.  For example, if the list
was [2, 3, 1] then it would be a three-layer network, with the
first layer containing 2 neurons, the second layer 3 neurons,
and the third layer 1 neuron.  The biases and weights for the
network are initialized randomly, using a Gaussian
distribution with mean 0, and variance 1.  Note that the first
layer is assumed to be an input layer, and by convention we
won't set any biases for those neurons, since biases are only
ever used in computing the outputs from later layers."""
self.num_layers = len(sizes)
self.sizes = sizes
self.biases = [np.random.randn(y, 1) for y in sizes[1:]]
self.weights = [np.random.randn(y, x)
for x, y in zip(sizes[:-1], sizes[1:])]

def feedforward(self, a):
"""Return the output of the network if a is input."""
for b, w in zip(self.biases, self.weights):
a = sigmoid(np.dot(w, a)+b)
return a

def SGD(self, training_data, epochs, mini_batch_size, eta,
test_data=None):
"""Train the neural network using mini-batch stochastic
gradient descent.  The training_data is a list of tuples
(x, y) representing the training inputs and the desired
outputs.  The other non-optional parameters are
self-explanatory.  If test_data is provided then the
network will be evaluated against the test data after each
epoch, and partial progress printed out.  This is useful for
tracking progress, but slows things down substantially."""
training_data = list(training_data)
test_data = list(test_data)
if test_data: n_test = len(test_data)
n = len(training_data)
for j in range(epochs):
random.shuffle(training_data)
mini_batches = [
training_data[k:k+mini_batch_size]
for k in range(0, n, mini_batch_size)]
for mini_batch in mini_batches:
self.update_mini_batch(mini_batch, eta)
if test_data:
print( "Epoch {0}: {1} / {2}".format(
j, self.evaluate(test_data), n_test))
else:
print( "Epoch {0} complete".format(j))

def update_mini_batch(self, mini_batch, eta):
"""Update the network's weights and biases by applying
gradient descent using backpropagation to a single mini batch.
The mini_batch is a list of tuples (x, y), and eta
is the learning rate."""
nabla_b = [np.zeros(b.shape) for b in self.biases]
nabla_w = [np.zeros(w.shape) for w in self.weights]
for x, y in mini_batch:
delta_nabla_b, delta_nabla_w = self.backprop(x, y)
nabla_b = [nb+dnb for nb, dnb in zip(nabla_b, delta_nabla_b)]
nabla_w = [nw+dnw for nw, dnw in zip(nabla_w, delta_nabla_w)]
self.weights = [w-(eta/len(mini_batch))*nw
for w, nw in zip(self.weights, nabla_w)]
self.biases = [b-(eta/len(mini_batch))*nb
for b, nb in zip(self.biases, nabla_b)]

def backprop(self, x, y):
"""Return a tuple (nabla_b, nabla_w) representing the
gradient for the cost function C_x.  nabla_b and
nabla_w are layer-by-layer lists of numpy arrays, similar
to self.biases and self.weights."""
nabla_b = [np.zeros(b.shape) for b in self.biases]
nabla_w = [np.zeros(w.shape) for w in self.weights]
# feedforward
activation = x
activations = [x] # list to store all the activations, layer by layer
zs = [] # list to store all the z vectors, layer by layer
for b, w in zip(self.biases, self.weights):
z = np.dot(w, activation)+b
zs.append(z)
activation = sigmoid(z)
activations.append(activation)
# backward pass
delta = self.cost_derivative(activations[-1], y) * \
sigmoid_prime(zs[-1])
nabla_b[-1] = delta
nabla_w[-1] = np.dot(delta, activations[-2].transpose())
# Note that the variable l in the loop below is used a little
# differently to the notation in Chapter 2 of the book.  Here,
# l = 1 means the last layer of neurons, l = 2 is the
# second-last layer, and so on.  It's a renumbering of the
# scheme in the book, used here to take advantage of the fact
# that Python can use negative indices in lists.
for l in range(2, self.num_layers):
z = zs[-l]
sp = sigmoid_prime(z)
delta = np.dot(self.weights[-l+1].transpose(), delta) * sp
nabla_b[-l] = delta
nabla_w[-l] = np.dot(delta, activations[-l-1].transpose())
return (nabla_b, nabla_w)

def evaluate(self, test_data):
"""Return the number of test inputs for which the neural
network outputs the correct result. Note that the neural
network's output is assumed to be the index of whichever
neuron in the final layer has the highest activation."""
test_results = [(np.argmax(self.feedforward(x)), y)
for (x, y) in test_data]
return sum(int(x == y) for (x, y) in test_results)

def cost_derivative(self, output_activations, y):
"""Return the vector of partial derivatives \partial C_x /
\partial a for the output activations."""
return (output_activations-y)

#### Miscellaneous functions
def sigmoid(z):
"""The sigmoid function."""
return 1.0/(1.0+np.exp(-z))

def sigmoid_prime(z):
"""Derivative of the sigmoid function."""
return sigmoid(z)*(1-sigmoid(z))

In [7]:
def vectorized_result(j):
"""Return a 10-dimensional unit vector with a 1.0 in the jth
position and zeroes elsewhere.  This is used to convert a digit
(0...9) into a corresponding desired output from the neural
network."""
e = np.zeros((10, 1))
e[j] = 1.0
return e

In [8]:
net = Network([784, 30, 10])

In [9]:
training_inputs = [np.reshape(x, (784, 1)) for x in X_train.copy()]
training_results = [vectorized_result(y) for y in y_train.copy()]
training_data = zip(training_inputs, training_results)

In [10]:
test_inputs = [np.reshape(x, (784, 1)) for x in X_test.copy()]
test_data = zip(test_inputs, y_test.copy())

In [11]:
net.SGD(training_data, 10, 10, 3.0, test_data=test_data)

Epoch 0: 1348 / 10000
Epoch 1: 1939 / 10000
Epoch 2: 2046 / 10000
Epoch 3: 1422 / 10000
Epoch 4: 1365 / 10000
Epoch 5: 1351 / 10000
Epoch 6: 1879 / 10000
Epoch 7: 1806 / 10000
Epoch 8: 1754 / 10000
Epoch 9: 1974 / 10000

In [12]:
net = Network([784, 10, 10])

training_inputs = [np.reshape(x, (784, 1)) for x in X_train.copy()]
training_results = [vectorized_result(y) for y in y_train.copy()]
training_data = zip(training_inputs, training_results)

test_inputs = [np.reshape(x, (784, 1)) for x in X_test.copy()]
test_data = zip(test_inputs, y_test.copy())

net.SGD(training_data, 10, 10, 1.0, test_data=test_data)

Epoch 0: 3526 / 10000
Epoch 1: 3062 / 10000
Epoch 2: 2946 / 10000
Epoch 3: 2462 / 10000
Epoch 4: 3617 / 10000
Epoch 5: 3773 / 10000
Epoch 6: 3568 / 10000
Epoch 7: 4459 / 10000
Epoch 8: 3009 / 10000
Epoch 9: 2660 / 10000