mnist_mlp_subset_regularized.py

'''Trains a simple deep NN on the MNIST dataset.

Choose a small subset of MNIST data and overfit it - get 100% accuracy (and 0 loss) on train data and 85% accuracy (and
some loss) on validation data

Then use dropout to fix overfitting (0.9 does the job)
'''

from __future__ import print_function

import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.optimizers import RMSprop, Adam
import matplotlib.pyplot as plt


batch_size = 128 # 128
num_classes = 10
epochs = 50

# the data, shuffled and split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

x_train = x_train.reshape(60000, 784)
x_train = x_train[:500, :]
y_train = y_train[:500]

x_test = x_test.reshape(10000, 784)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Dense(64, activation='relu', input_shape=(784,))) # 512
# model.add(Dropout(0.2))
# model.add(Dense(512, activation='relu'))
# model.add(Dropout(0.9))
model.add(Dense(10, activation='softmax'))
# model.add(Dense(10, activation='softmax', input_shape=(784,)))

model.summary()

model.compile(loss='categorical_crossentropy',
              optimizer=Adam(0.01),
              metrics=['accuracy'])

history = model.fit(x_train, y_train,
                    batch_size=batch_size,
                    epochs=epochs,
                    verbose=1,
                    validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

# summarize history for accuracy
plt.figure(0)
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
# plt.show()
# summarize history for loss
plt.figure(1)
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()