用Python实现神经网络(一)

Python实现神经网络有多种方法。这里我们使用keras框架。你必须安装 tensorflow或theano, 和 keras然后才能实现神经网络。

1. 下载数据集并提取训练和测试集(见“NN.ipynb”)

from keras.datasets import mnist

import matplotlib.pyplot as plt

%matplotlib inline

# load (downloaded if needed) the MNIST dataset

(X_train, y_train), (X_test, y_test) = mnist.load_data()

# plot 4 images as gray scale

plt.subplot(221)

plt.imshow(X_train[0], cmap=plt.get_cmap('gray'))

plt.subplot(222)

plt.imshow(X_train[1], cmap=plt.get_cmap('gray'))

plt.subplot(223)

plt.imshow(X_train[2], cmap=plt.get_cmap('gray'))

plt.subplot(224)

plt.imshow(X_train[3], cmap=plt.get_cmap('gray'))

# show the plot

plt.show()

图 4-18. 输出

2. 导入相关包:

import numpy as np

from keras.datasets import mnist

from keras.models import Sequential

from keras.layers import Dense

from keras.layers import Dropout

from keras.utils import np_utils

3. 预处理数据集:

num_pixels = X_train.shape[1] * X_train.shape[2]

# reshape the inputs so that they can be passed to the

vanilla NN

X_train = X_train.reshape(X_train.shape[0],num_pixels

).astype('float32')

X_test = X_test.reshape(X_test.shape[0],num_pixels).

astype('float32')

# scale inputs

X_train = X_train / 255

X_test = X_test / 255

# one hot encode the output

y_train = np_utils.to_categorical(y_train)

y_test = np_utils.to_categorical(y_test)

num_classes = y_test.shape[1]

4. 构建模型:

# building the model

model = Sequential()

# add 1000 units in the hidden layer

# apply relu activation in hidden layer

model.add(Dense(1000, input_dim=num_pixels,activation='relu'))

# initialize the output layer

model.add(Dense(num_classes, activation='softmax'))

# compile the model

model.compile(loss='categorical_crossentropy',optimizer='adam', metrics=['accuracy'])

# extract the summary of model

model.summary()

5. 运行模型:

model.fit(X_train, y_train, validation_data=(X_test,

y_test), epochs=5, batch_size=1024, verbose=1)

注意随着epochs增加, 测试集的准确率也增加。另外在keras里我们只要在第一层指明输入的维,它会自己动的推出余下各层的维。