【深度学习】【python】实现多层感知机并实验MINIST 中文注释版
环境要求
- python3.5
- tensorflow 1.4
- pytorch 0.2.0
程序如下:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""多层感知机"""
import numpy as np
import tensorflow as tf
import input_data
from logisticRegression import LogisticRegression
class HiddenLayer(object):
"""MLP隐含层"""
def __init__(self, inpt, n_in, n_out, W=None, b=None,
activation=tf.nn.sigmoid):
"""
-----------变量说明-----------------
inpt: tf.Tensor, 维度为 [n_examples, n_in]
n_in: int, 输入的维度
n_out: int, 隐含层单元数目
W, b: tf.Tensor, 权重和偏置
activation: tf.op, 激活函数
"""
# 未设定W;自行初始化;
if W is None:
bound_val = 4.0*np.sqrt(6.0/(n_in + n_out))
W = tf.Variable(tf.random_uniform([n_in, n_out], minval=-bound_val, maxval=bound_val),
dtype=tf.float32, name="W")
# 未设定b;自行初始化;
if b is None:
b = tf.Variable(tf.zeros([n_out,]), dtype=tf.float32, name="b")
self.W = W
self.b = b
# 计算输出;
sum_W = tf.matmul(inpt, self.W) + self.b
self.output = activation(sum_W) if activation is not None else sum_W
# 设置参数;
self.params = [self.W, self.b]
class MLP(object):
"""多层感知机类"""
def __init__(self, inpt, n_in, n_hidden, n_out):
"""
-----------变量说明-----------------
inpt: tf.Tensor, 维度为 [n_examples, n_in]
n_in: int, input的维度
n_hidden: int, 隐含层的单元数
n_out: int, output的维度
"""
# 定义隐含层;
self.hiddenLayer = HiddenLayer(inpt, n_in=n_in, n_out=n_hidden)
# 定义输出层(logistic layer);
self.outputLayer = LogisticRegression(self.hiddenLayer.output, n_in=n_hidden,
n_out=n_out)
# L1正则化;
self.L1 = tf.reduce_sum(tf.abs(self.hiddenLayer.W)) + \
tf.reduce_sum(tf.abs(self.outputLayer.W))
# L2正则化;
self.L2 = tf.reduce_sum(tf.square(self.hiddenLayer.W)) + \
tf.reduce_sum(tf.square(self.outputLayer.W))
# cross_entropy代价函数;
self.cost = self.outputLayer.cost
# 准确率计算函数;
self.accuracy = self.outputLayer.accuarcy
# 参数集合;
self.params = self.hiddenLayer.params + self.outputLayer.params
# 保持input更新;
self.input = inpt
if __name__ == "__main__":
# mnist数据集;
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# 定义输入输出占位符;
x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
# 声明mlp模型;
mlp_classifier = MLP(inpt=x, n_in=784, n_hidden=500, n_out=10)
# 计算cost;
l2_reg = 0.0001
cost = mlp_classifier.cost(y_) + l2_reg*mlp_classifier.L2
# 计算准确率;
accuracy = mlp_classifier.accuracy(y_)
# 模型给出的预测值;
predictor = mlp_classifier.outputLayer.y_pred
# 定义训练器;
train_op = tf.train.AdamOptimizer(learning_rate=0.01).minimize(
cost, var_list=mlp_classifier.params)
# 初始化所有变量;
init = tf.global_variables_initializer()
# 定义训练参数;
training_epochs = 10
batch_size = 100
display_step = 1
# 开始训练;
print("Start to train...")
with tf.Session() as sess:
# 执行初始化所有变量;
sess.run(init)
# 执行多个epoch;
for epoch in range(training_epochs):
# 训练参数;
avg_cost = 0.0
batch_num = int(mnist.train.num_examples / batch_size)
# 执行多个batch;
for i in range(batch_num):
# 获取当前batch的样本;
x_batch, y_batch = mnist.train.next_batch(batch_size)
# 训练;
sess.run(train_op, feed_dict={x: x_batch, y_: y_batch})
# 计算cost;
avg_cost += sess.run(cost, feed_dict={x: x_batch, y_: y_batch}) / batch_num
# 输出训练详情;
if epoch % display_step == 0:
val_acc = sess.run(accuracy, feed_dict={x: mnist.validation.images,
y_: mnist.validation.labels})
print("Epoch {0} cost: {1}, validation accuacy: {2}".format(epoch,
avg_cost, val_acc))
# 完成训练;输出预测和真实labels对比;
print("Finished!")
test_x = mnist.test.images[:10]
test_y = mnist.test.labels[:10]
print("Ture lables:")
print(" ", np.argmax(test_y, 1))
print("Prediction:")
print(" ", sess.run(predictor, feed_dict={x: test_x}))