TensorFlow人工智能引擎入门教程之八 接着补充一章MLP多层感知器网络原理以及 使用
这一章我们讲MLP 多层感知器 的使用，多层感知器 ，常用来做分类，效果非常好，比如文本分类，效果比SVM 贝叶斯 好多了，这些以前的机器学习很有名的算法，我现在基本不用它们，现在是深度学习 的AI时代。
多层感知器的介绍
MLP（多层感知器）神经网络是常见的ANN算法，它由一个输入层，一个输出层和一个或多个隐藏层组成。
在MLP中的所有神经元都差不多，每个神经元都有几个输入（连接前一层）神经元和输出（连接后一层）神经元，该神经元会将相同值传递给与之相连的多个输出神经元
一个神经网络训练网将一个特征向量作为输入，将该向量传递到隐藏层，然后通过权重和激励函数来计算结果，并将结果传递给下一层，直到最后传递给输出层才结束
首先我们来
下面是一个2层的多层感知器
其中 relu可以换成 tanh或者sigmoid
比如
tf.nn.sigmoid(tf.matmul(X, w_h)) #WX+B
def multilayer_perceptron(_X, _weights, _biases):
layer_1 = tf.nn.relu(tf.add(tf.matmul(_X, _weights['h1']), _biases['b1'])) #Hidden layer with RELU activation
layer_2 = tf.nn.relu(tf.add(tf.matmul(layer_1, _weights['h2']), _biases['b2'])) #Hidden layer with RELU activation
return tf.matmul(layer_2, _weights['out']) + _biases['out']
# Store layers weight & bias
weights = {
'h1': tf.Variable(tf.random_normal([n_input, 256])),
'h2': tf.Variable(tf.random_normal([256, 256])),
'out': tf.Variable(tf.random_normal([256, 10]))
}
biases = {
'b1': tf.Variable(tf.random_normal([256])),
'b2': tf.Variable(tf.random_normal([256])),
'out': tf.Variable(tf.random_normal([10]))
}
或者 修改成使用sigmoid
linear----线性感知器
tanh----双曲正切函数
sigmoid----双曲函数
softmax----1/(e(net) * e(wi*xi- shift))
log-softmax---- log(1/(e(net) * e(wi*xi)))
exp----指数函数
softplus----log(1+ e(wi*xi))
def multilayer_perceptron(_X, _weights, _biases): layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(_X, _weights['h1']), _biases['b1'])) #Hidden layer with sigmoid activation layer_2 = tf.nn.relu(tf.add(tf.matmul(layer_1, _weights['h2']), _biases['b2'])) #Hidden layer with RELU activation return tf.matmul(layer_2, _weights['out']) + _biases['out']
import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
import tensorflow as tf
# Parameters
learning_rate = 0.001
training_epochs = 15
batch_size = 100
display_step = 1
# Network Parameters
n_hidden_1 = 256 # 1st layer num features
n_hidden_2 = 256 # 2nd layer num features
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)
# tf Graph input
x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_classes])
# Create model
def multilayer_perceptron(_X, _weights, _biases):
layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(_X, _weights['h1']), _biases['b1'])) #Hidden layer with sigmoid activation
layer_2 = tf.nn.relu(tf.add(tf.matmul(layer_1, _weights['h2']), _biases['b2'])) #Hidden layer with RELU activation
return tf.matmul(layer_2, _weights['out']) + _biases['out']
# Store layers weight & bias
weights = {
'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes]))
}
biases = {
'b1': tf.Variable(tf.random_normal([n_hidden_1])),
'b2': tf.Variable(tf.random_normal([n_hidden_2])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
# Construct model
pred = multilayer_perceptron(x, weights, biases)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y)) # Softmax loss
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) # Adam Optimizer
# Initializing the variables
init = tf.initialize_all_variables()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
# Training cycle
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = int(mnist.train.num_examples/batch_size)
# Loop over all batches
for i in range(total_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
# Fit training using batch data
sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys})
# Compute average loss
avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys})/total_batch
# Display logs per epoch step
if epoch % display_step == 0:
print "Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost)
print "Optimization Finished!"
# Test model
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
# Calculate accuracy
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print "Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels})
下面我们运行测试 代码
