Last active
December 22, 2016 08:11
-
-
Save pyben/41d12f33c9a4717e3adf to your computer and use it in GitHub Desktop.
Revisions
-
pyben revised this gist
Jan 17, 2016 . 1 changed file with 40 additions and 34 deletions.There are no files selected for viewing
This file contains hidden or 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 charactersOriginal file line number Diff line number Diff line change @@ -1,38 +1,42 @@ import numpy as np from keras.datasets import imdb from keras.preprocessing.sequence import pad_sequences from keras.models import Sequential from keras.layers import containers from keras.layers.noise import GaussianNoise from keras.layers.core import Dense, AutoEncoder from keras.utils import np_utils from sklearn.metrics import (precision_score, recall_score, f1_score, accuracy_score) np.random.seed(1337) max_len = 800 max_words = 20000 batch_size = 64 nb_classes = 2 nb_epoch = 2 nb_hidden_layers = [800, 500, 300, 100] nb_noise_layers = [0.6, 0.4, 0.3, ] (X_train, y_train), (X_test, y_test) = \ imdb.load_data(nb_words=max_words, test_split=0.2) X_train = pad_sequences(X_train, maxlen=max_len, dtype='float32') X_test = pad_sequences(X_test, maxlen=max_len, dtype='float32') X_train_tmp = np.copy(X_train) y_train = np.asarray(y_train) y_test = np.asarray(y_test) Y_train = np_utils.to_categorical(y_train, nb_classes) Y_test = np_utils.to_categorical(y_test, nb_classes) print('Train: {}'.format(X_train.shape)) print('Test: {}'.format(X_test.shape)) trained_encoders = [] for i, (n_in, n_out) in enumerate( zip(nb_hidden_layers[:-1], nb_hidden_layers[1:]), start=1): @@ -42,34 +46,36 @@ ae = Sequential() encoder = containers.Sequential([ GaussianNoise(nb_noise_layers[i - 1], input_shape=(n_in,)), Dense(input_dim=n_in, output_dim=n_out, activation='sigmoid'), ]) decoder = 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='rmsprop') ae.fit(X_train_tmp, X_train_tmp, batch_size=batch_size, nb_epoch=nb_epoch) trained_encoders.append(ae.layers[0].encoder) X_train_tmp = ae.predict(X_train_tmp) model = Sequential() for encoder in trained_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='rmsprop') model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch, show_accuracy=True, validation_data=(X_test, Y_test)) y_pred = model.predict_classes(X_test) accuracy = accuracy_score(y_test, y_pred) recall = recall_score(y_test, y_pred) precision = precision_score(y_test, y_pred) f1 = f1_score(y_test, y_pred) print('Accuracy: {}'.format(accuracy)) print('Recall: {}'.format(recall)) print('Precision: {}'.format(precision)) print('F1: {}'.format(f1)) -
Jan 13, 2016 .There are no files selected for viewing
This file contains hidden or 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 charactersOriginal file line number Diff line number Diff line change @@ -0,0 +1,75 @@ from __future__ import absolute_import from __future__ import print_function import numpy as np np.random.seed(1337) # for reproducibility 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.utils import np_utils batch_size = 64 nb_classes = 10 nb_epoch = 0 nb_hidden_layers = [784, 600, 500, 400] nb_noise_layers = [0.5, 0.2, 0.1, ] # 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(-1, 784) X_test = X_test.reshape(-1, 784) X_train = X_train.astype("float32") / 255.0 X_test = X_test.astype("float32") / 255.0 print(X_train.shape[0], 'train samples') print(X_test.shape[0], 'test samples') # convert class vectors to binary class matrices Y_train = np_utils.to_categorical(y_train, nb_classes) Y_test = np_utils.to_categorical(y_test, nb_classes) # Layer-wise pre-training trained_encoders = [] X_train_tmp = X_train for i, (n_in, n_out) in enumerate( zip(nb_hidden_layers[:-1], nb_hidden_layers[1:]), start=1): print('Pre-training the layer: Input {} -> Output {}' .format(n_in, n_out)) ae = Sequential() encoder = containers.Sequential([ GaussianNoise(nb_noise_layers[i - 1], input_shape=(n_in,)), Dense(input_dim=n_in, output_dim=n_out, init='uniform', 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='rmsprop') ae.fit(X_train_tmp, X_train_tmp, batch_size=batch_size, nb_epoch=nb_epoch) # Store trainined weight trained_encoders.append(ae.layers[0].encoder) # Update training data X_train_tmp = ae.predict(X_train_tmp) # Fine-tuning print('Fine-tuning') model = Sequential() for encoder in trained_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='rmsprop') 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:', score[0]) print('Test accuracy:', score[1])