demo48.py

from keras import layers
from keras import models
from keras.datasets import imdb
import numpy as np

(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)
print(train_data[0])
print(max([max(sequence) for sequence in train_data]))

word_index = imdb.get_word_index()
reverse_word_index = dict([(v, k) for k, v in word_index.items()])
for k in range(5):
    decoded_review = ' '.join([reverse_word_index.get(i - 3, '?') for i in train_data[k]])
    print(decoded_review)
print(train_labels[:5])


def vectorize_sequence(sequences, dimension=10000):
    results = np.zeros((len(sequences), dimension))
    for i, sequence in enumerate(sequences):
        results[i, sequence] = 1.
    return results

x_train = vectorize_sequence(train_data)
x_test = vectorize_sequence(test_data)
y_train = np.asarray(train_labels).astype('float32')
y_test = np.asarray(test_labels).astype('float32')
print(x_train.shape, x_test.shape, y_train.shape, y_test.shape)
print(x_train[0])

model = models.Sequential()
model.add(layers.Dense(32, activation='relu', input_shape=(10000,)))
model.add(layers.Dense(16, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop', loss='binary_crossentropy',metrics=['accuracy'])
model.summary()

x_val = x_train[:10000]
partial_x_train = x_train[10000:]
y_val = y_train[:10000]
partial_y_train = y_train[10000:]

model.fit(partial_x_train, partial_y_train, epochs=20, batch_size=128)