I have a computing project where I want my program to recognise handwritten letters and numbers. I started off by creating a program that can recognise numbers from the MNIST dataset and works just fine. I used a CNN (Convolutional Neural Network) from Michael Nielson's book (see code below for the neural network). I was wondering how I can implement EMNIST into this now (as MNIST is already a part of the NIST and EMNIST dataset and layed out in a similar format as well (I think)).
import random
import json
import numpy as np
import matplotlib.pyplot as plt
def load(filename):
"""Load a neural network from the file ``filename``. Returns an
instance of Network.
"""
print("loading dataset...")
f = open(filename, "r")
data = json.load(f)
f.close()
net = Network(data["sizes"])
net.weights = [np.array(w) for w in data["weights"]]
net.biases = [np.array(b) for b in data["biases"]]
return net
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)
n = len(training_data)
if test_data:
test_data = list(test_data)
n_test = len(test_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 {} : {} / {}".format(j,self.evaluate(test_data),n_test));
if j == epochs-1:
self.save("model1")
else:
print("Epoch {} 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)
def save(self, filename):
"""Save the neural network to the file ``filename``."""
data = {"sizes": self.sizes,
"weights": [w.tolist() for w in self.weights],
"biases": [b.tolist() for b in self.biases]}
f = open(filename, "w")
json.dump(data, f)
f.close()
def test(self, img):
saveImg = cv2.resize(img, (28, 28))
gray = rgb2gray(saveImg)
gray2 = inverte(gray)
cv2.imshow("orig 28x28", saveImg)
cv2.imshow("gray 28x28", gray)
cv2.imshow("inverte 28x28", gray2)
cv2.imwrite("28x28.jpg", gray2)
imgInput = np.reshape(gray2, (784, 1))
result = np.argmax(self.feedforward(imgInput))
return result
#### Miscellaneous functions
def sigmoid(z):
return 1.0/(1.0+np.exp(-z))
def sigmoid_prime(z):
return sigmoid(z)*(1-sigmoid(z))
def rgb2gray(rgb):
return np.dot(rgb[...,:3], [0.299, 0.587, 0.114])
def inverte(imagem):
return (255-imagem)
def getImg(img, net):
result = net.test(img)
num = 0
print("Output is: " + str(result))
import mnist_loader #loading the mnist dataset
import cv2
training_data, validation_data, test_data = mnist_loader.load_data_wrapper()
import os
if os.path.exists("model1") == False:
print("model1.json doesn't exist")
net = Network([784, 30, 10])
net.SGD(training_data, 44, 10, 0.5, test_data=test_data)
else:
print("model1 already exists")
net = load("model1")
print("completed loading")
for x in range(1, 2):
name = "thick1.jpg"
print(name)
image = cv2.imread(name)
cv2.resize(image, (28,28))
getImg(image, net)
