Created
February 10, 2016 10:28
-
-
Save cadrev/10d7c9ef3c2e98df1a6e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
# | |
# This is an implementation of adenoising autoencoder as | |
# described on the following paper: | |
# http://www.jmlr.org/papers/volume11/vincent10a/vincent10a.pdf | |
# | |
import numpy as np | |
from keras.datasets import mnist | |
from keras.models import Sequential | |
from keras.layers import containers | |
from keras.layers.core import Dense, AutoEncoder | |
from keras.layers.noise import GaussianNoise | |
from keras.optimizers import RMSprop | |
from keras.utils import np_utils | |
np.random.seed(1337) | |
batch_size = 128 | |
nb_classes = 10 | |
nb_epoch = 20 | |
nb_hidden_layers = [784, 600, 500, 400, ] | |
nb_noise = [0.3, 0.2, 0.1, ] | |
(X_train, y_train), (X_test, y_test) = mnist.load_data() | |
X_train = X_train.reshape(60000, 784) | |
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('Train samples: {}'.format(X_train.shape[0])) | |
print('Test samples: {}'.format(X_test.shape[0])) | |
Y_train = np_utils.to_categorical(y_train, nb_classes) | |
Y_test = np_utils.to_categorical(y_test, nb_classes) | |
encoders = [] | |
X_train_tmp = np.copy(X_train) | |
rms = RMSprop() | |
for i, (n_in, n_out) in enumerate( | |
zip(nb_hidden_layers[:-1], nb_hidden_layers[1:]), start=1): | |
print('Training the layer {}: Input {} -> Output {}'.format( | |
i, n_in, n_out)) | |
ae = Sequential() | |
encoder = containers.Sequential([ | |
GaussianNoise(nb_noise[i - 1], input_shape=(n_in,)), | |
Dense(input_dim=n_in, output_dim=n_out, activation='sigmoid') | |
]) | |
decoder = containers.Sequential([ | |
Dense(input_dim=n_out, output_dim=n_in, activation='sigmoid') | |
]) | |
ae.add(AutoEncoder( | |
encoder=encoder, decoder=decoder, | |
output_reconstruction=False, | |
)) | |
ae.compile(loss='mean_squared_error', optimizer=rms) | |
ae.fit(X_train_tmp, X_train_tmp, | |
batch_size=batch_size, nb_epoch=nb_epoch) | |
encoders.append(ae.layers[0].encoder) | |
X_train_tmp = ae.predict(X_train_tmp) | |
model = Sequential() | |
for encoder in encoders: | |
model.add(encoder) | |
model.add(Dense( | |
input_dim=nb_hidden_layers[-1], output_dim=nb_classes, | |
activation='softmax')) | |
model.compile(loss='categorical_crossentropy', optimizer=rms) | |
score = model.evaluate(X_test, Y_test, show_accuracy=True, verbose=0) | |
print('Test score before fine turning: {}'.format(score[0])) | |
print('Test accuracy before fine turning: {}'.format(score[1])) | |
model.fit( | |
X_train, Y_train, batch_size=batch_size, | |
nb_epoch=nb_epoch, show_accuracy=True, | |
validation_data=(X_test, Y_test) | |
) | |
score = model.evaluate(X_test, Y_test, show_accuracy=True, verbose=0) | |
print('Test score after fine turning: {}'.format(score[0])) | |
print('Test accuracy after fine turning: {}'.format(score[1])) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment