利用keras自带路透社数据集进行多分类训练

 import numpy as np
 from keras.datasets import reuters
 from keras import layers
 from keras import models
 from keras import optimizers
 from keras.utils.np_utils import to_categorical
 import matplotlib.pyplot as plt

 def vectorize_data(x, dim = 10000):
     res = np.zeros((len(x), dim))
     for i, sequence in enumerate(x):
         res[i, sequence] = 1
     return res

 def main():
     (train_data, train_labels), (test_data, test_labels) = reuters.load_data(num_words=10000)
     x_train = vectorize_data(train_data)
     x_test = vectorize_data(test_data)
     y_train = to_categorical(train_labels)
     y_test = to_categorical(test_labels)

     network = models.Sequential()
     network.add(layers.Dense(128, activation = 'relu', input_shape = (10000, )))
     network.add(layers.Dense(64, activation = 'relu'))
     network.add(layers.Dense(46, activation = 'softmax'))

     network.compile(optimizer = 'rmsprop', loss = 'categorical_crossentropy', metrics = ['accuracy'])
     network.fit(x_train, y_train, epochs = 6, batch_size = 512)

     _, acc = network.evaluate(x_test, y_test)

     print(acc)

 if __name__ == "__main__":
     main()