官网实例详解4.39（reuters_mlp_relu_vs_selu.py）-keras学习笔记四

将自正规化MLP与常规MLP进行比较

Keras实例目录

代码注释

'''Compares self-normalizing MLPs with regular MLPs.
将自正规化MLP与常规MLP进行比较
Compares the performance of a simple MLP using two
different activation functions: RELU and SELU
on the Reuters newswire topic classification task.
比较两个不同的激活函数：Relu和SELU在路透社新闻线主题（数据集）分类任务的在简单的MLP（多层感知机）的性能。
# Reference
参考
- Klambauer, G., Unterthiner, T., Mayr, A., & Hochreiter, S. (2017).
  Self-Normalizing Neural Networks. arXiv preprint arXiv:1706.02515.
  https://arxiv.org/abs/1706.02515
'''
from __future__ import print_function

import numpy as np
import matplotlib.pyplot as plt
import keras
from keras.datasets import reuters
from keras.models import Sequential
from keras.layers import Dense, Activation, Dropout
from keras.layers.noise import AlphaDropout
from keras.preprocessing.text import Tokenizer

max_words = 1000
batch_size = 16
epochs = 40
plot = True


def create_network(n_dense=6,
                   dense_units=16,
                   activation='selu',
                   dropout=AlphaDropout,
                   dropout_rate=0.1,
                   kernel_initializer='lecun_normal',
                   optimizer='adam',
                   num_classes=1,
                   max_words=max_words):
    """Generic function to create a fully-connected neural network.
    本函数创建一个全连接的神经网络。

    # Arguments
    参数
        n_dense: int > 0. Number of dense layers.
        n_dense: int > 0. 全连接数量
        dense_units: int > 0. Number of dense units per layer.
        dense_units: int > 0. 每层全连接单元的数量
        dropout: keras.layers.Layer. A dropout layer to apply.
        dropout: keras.layers.Layer. 一个dropout层去应用
        dropout_rate: 0 <= float <= 1. The rate of dropout.
        dropout_rate: 0 <= float <= 1. dropout的比率
        kernel_initializer: str. The initializer for the weights.
        kernel_initializer: str. 权重初始化.
        optimizer: str/keras.optimizers.Optimizer. The optimizer to use.
        num_classes: int > 0. The number of classes to predict.
        num_classes: int > 0. 类别量.
        max_words: int > 0. The maximum number of words per data point.
        max_words: int > 0. 每个数据点的最大单词数。

    # Returns
    返回
        A Keras model instance (compiled).
        Keras模型实例（编译）
    """
    model = Sequential()
    model.add(Dense(dense_units, input_shape=(max_words,),
                    kernel_initializer=kernel_initializer))
    model.add(Activation(activation))
    model.add(dropout(dropout_rate))

    for i in range(n_dense - 1):
        model.add(Dense(dense_units, kernel_initializer=kernel_initializer))
        model.add(Activation(activation))
        model.add(dropout(dropout_rate))

    model.add(Dense(num_classes))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])
    return model


network1 = {
    'n_dense': 6,
    'dense_units': 16,
    'activation': 'relu',
    'dropout': Dropout,
    'dropout_rate': 0.5,
    'kernel_initializer': 'glorot_uniform',
    'optimizer': 'sgd'
}

network2 = {
    'n_dense': 6,
    'dense_units': 16,
    'activation': 'selu',
    'dropout': AlphaDropout,
    'dropout_rate': 0.1,
    'kernel_initializer': 'lecun_normal',
    'optimizer': 'sgd'
}

print('Loading data...')
(x_train, y_train), (x_test, y_test) = reuters.load_data(num_words=max_words,
                                                         test_split=0.2)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')

num_classes = np.max(y_train) + 1
print(num_classes, 'classes')

print('Vectorizing sequence data...')
tokenizer = Tokenizer(num_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 = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
print('y_train shape:', y_train.shape)
print('y_test shape:', y_test.shape)

print('\nBuilding network 1...')

model1 = create_network(num_classes=num_classes, **network1)
history_model1 = model1.fit(x_train,
                            y_train,
                            batch_size=batch_size,
                            epochs=epochs,
                            verbose=1,
                            validation_split=0.1)

score_model1 = model1.evaluate(x_test,
                               y_test,
                               batch_size=batch_size,
                               verbose=1)


print('\nBuilding network 2...')
model2 = create_network(num_classes=num_classes, **network2)

history_model2 = model2.fit(x_train,
                            y_train,
                            batch_size=batch_size,
                            epochs=epochs,
                            verbose=1,
                            validation_split=0.1)

score_model2 = model2.evaluate(x_test,
                               y_test,
                               batch_size=batch_size,
                               verbose=1)

print('\nNetwork 1 results')
print('Hyperparameters:', network1)
print('Test score:', score_model1[0])
print('Test accuracy:', score_model1[1])
print('Network 2 results')
print('Hyperparameters:', network2)
print('Test score:', score_model2[0])
print('Test accuracy:', score_model2[1])

plt.plot(range(epochs),
         history_model1.history['val_loss'],
         'g-',
         label='Network 1 Val Loss')
plt.plot(range(epochs),
         history_model2.history['val_loss'],
         'r-',
         label='Network 2 Val Loss')
plt.plot(range(epochs),
         history_model1.history['loss'],
         'g--',
         label='Network 1 Loss')
plt.plot(range(epochs),
         history_model2.history['loss'],
         'r--',
         label='Network 2 Loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.savefig('comparison_of_networks.png')

代码执行

 

Keras详细介绍

英文：https://keras.io/

中文：http://keras-cn.readthedocs.io/en/latest/

实例下载

https://github.com/keras-team/keras

https://github.com/keras-team/keras/tree/master/examples

完整项目下载

方便没积分童鞋，请加企鹅452205574，共享文件夹。

包括：代码、数据集合（图片）、已生成model、安装库文件等。