59 lines
1.9 KiB
Python
59 lines
1.9 KiB
Python
'''Trains and evaluate a simple MLP
|
|
on the Reuters newswire topic classification task.
|
|
'''
|
|
|
|
from __future__ import print_function
|
|
import numpy as np
|
|
np.random.seed(1337) # for reproducibility
|
|
|
|
from keras.datasets import reuters
|
|
from keras.models import Sequential
|
|
from keras.layers import Dense, Dropout, Activation
|
|
from keras.utils import np_utils
|
|
from keras.preprocessing.text import Tokenizer
|
|
|
|
max_words = 1000
|
|
batch_size = 32
|
|
nb_epoch = 5
|
|
|
|
print('Loading data...')
|
|
(X_train, y_train), (X_test, y_test) = reuters.load_data(nb_words=max_words, test_split=0.2)
|
|
print(len(X_train), 'train sequences')
|
|
print(len(X_test), 'test sequences')
|
|
|
|
nb_classes = np.max(y_train)+1
|
|
print(nb_classes, 'classes')
|
|
|
|
print('Vectorizing sequence data...')
|
|
tokenizer = Tokenizer(nb_words=max_words)
|
|
X_train = tokenizer.sequences_to_matrix(X_train, mode='binary')
|
|
X_test = tokenizer.sequences_to_matrix(X_test, mode='binary')
|
|
print('X_train shape:', X_train.shape)
|
|
print('X_test shape:', X_test.shape)
|
|
|
|
print('Convert class vector to binary class matrix (for use with categorical_crossentropy)')
|
|
Y_train = np_utils.to_categorical(y_train, nb_classes)
|
|
Y_test = np_utils.to_categorical(y_test, nb_classes)
|
|
print('Y_train shape:', Y_train.shape)
|
|
print('Y_test shape:', Y_test.shape)
|
|
|
|
print('Building model...')
|
|
model = Sequential()
|
|
model.add(Dense(512, input_shape=(max_words,)))
|
|
model.add(Activation('relu'))
|
|
model.add(Dropout(0.5))
|
|
model.add(Dense(nb_classes))
|
|
model.add(Activation('softmax'))
|
|
|
|
model.compile(loss='categorical_crossentropy',
|
|
optimizer='adam',
|
|
metrics=['accuracy'])
|
|
|
|
history = model.fit(X_train, Y_train,
|
|
nb_epoch=nb_epoch, batch_size=batch_size,
|
|
verbose=1, validation_split=0.1)
|
|
score = model.evaluate(X_test, Y_test,
|
|
batch_size=batch_size, verbose=1)
|
|
print('Test score:', score[0])
|
|
print('Test accuracy:', score[1])
|