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

Convolution Nets for MNIST

Deep Learning models can take quite a bit of time to run, particularly if GPU isn't used.

In the interest of time, you could sample a subset of observations (e.g. $1000$) that are a particular number of your choice (e.g. $6$) and $1000$ observations that aren't that particular number (i.e. $\neq 6$).

We will build a model using that and see how it performs on the test dataset

python

#Import the required libraries
import numpy as np
np.random.seed(1338)

from keras.datasets import mnist

python

from keras.models import Sequential

python

from keras.layers.core import Dense, Dropout, Activation, Flatten

python

from keras.layers.convolutional import Convolution2D
from keras.layers.pooling import MaxPooling2D

python

from keras.utils import np_utils
from keras.optimizers import SGD

Loading Data

python

path_to_dataset = "euroscipy_2016_dl-keras/data/mnist.pkl.gz"

#Load the training and testing data
(X_train, y_train), (X_test, y_test) = mnist.load_data(path_to_dataset)

python

X_test_orig = X_test

Data Preparation

python

img_rows, img_cols = 28, 28

X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)

X_train = X_train.astype('float32')
X_test = X_test.astype('float32')

X_train /= 255
X_test /= 255

python

# Seed for reproducibilty
np.random.seed(1338)

# Test data
X_test = X_test.copy()
Y = y_test.copy()

# Converting the output to binary classification(Six=1,Not Six=0)
Y_test = Y == 6
Y_test = Y_test.astype(int)

# Selecting the 5918 examples where the output is 6
X_six = X_train[y_train == 6].copy()
Y_six = y_train[y_train == 6].copy()

# Selecting the examples where the output is not 6
X_not_six = X_train[y_train != 6].copy()
Y_not_six = y_train[y_train != 6].copy()

# Selecting 6000 random examples from the data that 
# only contains the data where the output is not 6
random_rows = np.random.randint(0,X_six.shape[0],6000)
X_not_six = X_not_six[random_rows]
Y_not_six = Y_not_six[random_rows]

python

# Appending the data with output as 6 and data with output as <> 6
X_train = np.append(X_six,X_not_six)

# Reshaping the appended data to appropraite form
X_train = X_train.reshape(X_six.shape[0] + X_not_six.shape[0], 
                          1, img_rows, img_cols)

# Appending the labels and converting the labels to 
# binary classification(Six=1,Not Six=0)
Y_labels = np.append(Y_six,Y_not_six)
Y_train = Y_labels == 6 
Y_train = Y_train.astype(int)

python

print(X_train.shape, Y_labels.shape, X_test.shape, Y_test.shape)

python

# Converting the classes to its binary categorical form
nb_classes = 2
Y_train = np_utils.to_categorical(Y_train, nb_classes)
Y_test = np_utils.to_categorical(Y_test, nb_classes)

A simple CNN

python

#Initializing the values for the convolution neural network
nb_epoch = 2
batch_size = 128
# number of convolutional filters to use
nb_filters = 32
# size of pooling area for max pooling
nb_pool = 2
# convolution kernel size
nb_conv = 3

sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)

Step 1: Model Definition

python

model = Sequential()

model.add(Convolution2D(nb_filters, nb_conv, nb_conv,
                        border_mode='valid',
                        input_shape=(1, img_rows, img_cols)))
model.add(Activation('relu'))

model.add(Flatten())
model.add(Dense(nb_classes))
model.add(Activation('softmax'))

Step 2: Compile

python

model.compile(loss='categorical_crossentropy',
              optimizer='sgd',
              metrics=['accuracy'])

Step 3: Fit

python

model.fit(X_train, Y_train, batch_size=batch_size, 
          nb_epoch=nb_epoch,verbose=1,
          validation_data=(X_test, Y_test))

Step 4: Evaluate

python

# Evaluating the model on the test data    
score, accuracy = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score)
print('Test accuracy:', accuracy)

Let's plot our model Predictions!

python

import matplotlib.pyplot as plt

%matplotlib inline

python

slice = 15
predicted = model.predict(X_test[:slice]).argmax(-1)

plt.figure(figsize=(16,8))
for i in range(slice):
    plt.subplot(1, slice, i+1)
    plt.imshow(X_test_orig[i], interpolation='nearest')
    plt.text(0, 0, predicted[i], color='black', 
             bbox=dict(facecolor='white', alpha=1))
    plt.axis('off')

Adding more Dense Layers

python

model = Sequential()
model.add(Convolution2D(nb_filters, nb_conv, nb_conv,
                        border_mode='valid',
                        input_shape=(1, img_rows, img_cols)))
model.add(Activation('relu'))

model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))

model.add(Dense(nb_classes))
model.add(Activation('softmax'))

python

model.compile(loss='categorical_crossentropy',
              optimizer='sgd',
              metrics=['accuracy'])

model.fit(X_train, Y_train, batch_size=batch_size, 
          nb_epoch=nb_epoch,verbose=1,
          validation_data=(X_test, Y_test))

python

#Evaluating the model on the test data    
score, accuracy = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score)
print('Test accuracy:', accuracy)

Adding Dropout

python

model = Sequential()

model.add(Convolution2D(nb_filters, nb_conv, nb_conv,
                        border_mode='valid',
                        input_shape=(1, img_rows, img_cols)))
model.add(Activation('relu'))

model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))

python

model.compile(loss='categorical_crossentropy',
              optimizer='sgd',
              metrics=['accuracy'])

model.fit(X_train, Y_train, batch_size=batch_size, 
          nb_epoch=nb_epoch,verbose=1,
          validation_data=(X_test, Y_test))

python

#Evaluating the model on the test data    
score, accuracy = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score)
print('Test accuracy:', accuracy)

Adding more Convolution Layers

python

model = Sequential()
model.add(Convolution2D(nb_filters, nb_conv, nb_conv,
                        border_mode='valid',
                        input_shape=(1, img_rows, img_cols)))
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters, nb_conv, nb_conv))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))
model.add(Dropout(0.25))
    
model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))

python

model.compile(loss='categorical_crossentropy',
              optimizer='sgd',
              metrics=['accuracy'])

model.fit(X_train, Y_train, batch_size=batch_size, 
          nb_epoch=nb_epoch,verbose=1,
          validation_data=(X_test, Y_test))

python

#Evaluating the model on the test data    
score, accuracy = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score)
print('Test accuracy:', accuracy)

Exercise

The above code has been written as a function.

Change some of the hyperparameters and see what happens.

python

# Function for constructing the convolution neural network
# Feel free to add parameters, if you want

def build_model():
    """"""
    model = Sequential()
    model.add(Convolution2D(nb_filters, nb_conv, nb_conv,
                        border_mode='valid',
                        input_shape=(1, img_rows, img_cols)))
    model.add(Activation('relu'))
    model.add(Convolution2D(nb_filters, nb_conv, nb_conv))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))
    model.add(Dropout(0.25))
    
    model.add(Flatten())
    model.add(Dense(128))
    model.add(Activation('relu'))
    model.add(Dropout(0.5))
    model.add(Dense(nb_classes))
    model.add(Activation('softmax'))
    
    model.compile(loss='categorical_crossentropy',
              optimizer='sgd',
              metrics=['accuracy'])

    model.fit(X_train, Y_train, batch_size=batch_size, 
              nb_epoch=nb_epoch,verbose=1,
              validation_data=(X_test, Y_test))
          

    #Evaluating the model on the test data    
    score, accuracy = model.evaluate(X_test, Y_test, verbose=0)
    print('Test score:', score)
    print('Test accuracy:', accuracy)

python

#Timing how long it takes to build the model and test it.
%timeit -n1 -r1 build_model()

Batch Normalisation

Normalize the activations of the previous layer at each batch, i.e. applies a transformation that maintains the mean activation close to 0 and the activation standard deviation close to 1.

How to BatchNorm in Keras

python

from keras.layers.normalization import BatchNormalization

BatchNormalization(epsilon=1e-06, mode=0, 
                   axis=-1, momentum=0.99, 
                   weights=None, beta_init='zero', 
                   gamma_init='one')

python

# Try to add a new BatchNormalization layer to the Model 
# (after the Dropout layer)