TensorFlow入门-不同网络模型 - mnist手写数字 - 识别效果对比
不同网络模型 - mnist手写数字 - 识别效果对比
1.1 网络模型
- 单神经元
- 单神经元+MAXOUT
- 多层神经元 二层
- 多层神经元 三层
2.1 单神经元代码
# -*- coding: utf-8 -*-
import pylab
import tensorflow as tf # 导入tensorflow库
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
tf.reset_default_graph()
# tf Graph Input
x = tf.placeholder(tf.float32, [None, 784]) # mnist data维度 28*28=784
y = tf.placeholder(tf.float32, [None, 10]) # 0-9 数字=> 10 classes
# Set model weights
W = tf.Variable(tf.random_normal([784, 10]))
b = tf.Variable(tf.zeros([10]))
# 构建模型
pred = tf.nn.softmax(tf.matmul(x, W) + b) # Softmax分类
# Minimize error using cross entropy
cost = tf.reduce_mean(-tf.reduce_sum(y * tf.log(pred), reduction_indices=1))
# 参数设置
learning_rate = 0.04
# 使用梯度下降优化器
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
training_epochs = 200
batch_size = 100
display_step = 1
saver = tf.train.Saver()
model_path = "log1/Date.ckpt"
# 启动session
with tf.Session() as sess:
sess.run(tf.global_variables_initializer()) # Initializing OP
# 启动循环开始训练
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = int(mnist.train.num_examples / batch_size)
# 遍历全部数据集
for i in range(total_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
# Run optimization op (backprop) and cost op (to get loss value)
_, c = sess.run([optimizer, cost], feed_dict={
x: batch_xs,
y: batch_ys})
# Compute average loss
avg_cost += c / total_batch
# 显示训练中的详细信息
if (epoch + 1) % display_step == 0:
print("Epoch:", '%04d' % (epoch + 1), "cost=", "{:.9f}".format(avg_cost))
print(" Finished!")
# Save model weights to disk
save_path = saver.save(sess, model_path)
print("Model saved in file: %s" % save_path)
# 读取模型
print("Starting 2nd session...")
with tf.Session() as sess:
# Initialize variables
sess.run(tf.global_variables_initializer()) # 初始化模型
# Restore model weights from previously saved model
saver.restore(sess, model_path) # 恢复模型
# pred ("Softmax:0", shape=(?, 10), dtype=float32)
# y ("Placeholder_1:0", shape=(?, 10), dtype=float32)
# 测试 model
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
# 计算准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print("模型一准确率:", accuracy.eval({
x: mnist.test.images, y: mnist.test.labels}))
output = tf.argmax(pred, 1)
batch_xs, batch_ys = mnist.train.next_batch(2)
outputval, predv = sess.run([output, pred], feed_dict={
x: batch_xs})
print(outputval, batch_ys)
im = batch_xs[0]
im = im.reshape(-1, 28)
pylab.imshow(im)
pylab.show()
im = batch_xs[1]
im = im.reshape(-1, 28)
pylab.imshow(im)
pylab.show()
2.2 单神经元+MAXOUT
# -*- coding: utf-8 -*-
import pylab
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/")
import tensorflow as tf # 导入tensorflow库
def max_out(inputs, num_units, axis=None):
shape = inputs.get_shape().as_list()
if shape[0] is None:
shape[0] = -1
if axis is None: # Assume that channel is the last dimension
axis = -1
num_channels = shape[axis]
if num_channels % num_units:
raise ValueError('number of features({}) is not '
'a multiple of num_units({})'.format(num_channels, num_units))
shape[axis] = num_units
shape += [num_channels // num_units]
outputs = tf.reduce_max(tf.reshape(inputs, shape), -1, keep_dims=False)
return outputs
tf.reset_default_graph()
# tf Graph Input
x = tf.placeholder(tf.float32, [None, 784]) # mnist data维度 28*28=784
y = tf.placeholder(tf.int32, [None]) # 0-9 数字=> 10 classes
# Set model weights
W = tf.Variable(tf.random_normal([784, 100]))
b = tf.Variable(tf.zeros([100]))
z = tf.matmul(x, W) + b
maxout = max_out(z, 50)
# Set model weights
W2 = tf.Variable(tf.truncated_normal([50, 10], stddev=0.1))
b2 = tf.Variable(tf.zeros([10]))
# 构建模型
pred = tf.matmul(maxout, W2) + b2
# Minimize error using cross entropy
cost = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y, logits=pred))
# 参数设置
learning_rate = 0.04
# 使用梯度下降优化器
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
training_epochs = 200
batch_size = 100
display_step = 1
saver = tf.train.Saver()
model_path = "log2/Date.ckpt"
# 启动session
with tf.Session() as sess:
sess.run(tf.global_variables_initializer()) # Initializing OP
# 启动循环开始训练
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = int(mnist.train.num_examples / batch_size)
# 遍历全部数据集
for i in range(total_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
# Run optimization op (backprop) and cost op (to get loss value)
_, c = sess.run([optimizer, cost], feed_dict={
x: batch_xs,
y: batch_ys})
# Compute average loss
avg_cost += c / total_batch
# 显示训练中的详细信息
if (epoch + 1) % display_step == 0:
print("Epoch:", '%04d' % (epoch + 1), "cost=", "{:.9f}".format(avg_cost))
print(" Finished!")
# Save model weights to disk
save_path = saver.save(sess, model_path)
print("Model saved in file: %s" % save_path)
# 读取模型
print("Starting 2nd session...")
with tf.Session() as sess:
# Initialize variables
sess.run(tf.global_variables_initializer()) # 初始化模型
# Restore model weights from previously saved model
saver.restore(sess, model_path) # 恢复模型
# 测试 model
# pred Tensor("add_1:0", shape=(?, 10), dtype=float32)
# y Tensor("Placeholder_1:0", shape=(?,), dtype=int32)
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.cast(y, tf.int64))
# 计算准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print("模型二准确率:", accuracy.eval({
x: mnist.test.images, y: mnist.test.labels}))
output = tf.argmax(pred, 1)
batch_xs, batch_ys = mnist.train.next_batch(2)
outputval, predv = sess.run([output, pred], feed_dict={
x: batch_xs})
print(outputval, batch_ys)
im = batch_xs[0]
im = im.reshape(-1, 28)
pylab.imshow(im)
pylab.show()
im = batch_xs[1]
im = im.reshape(-1, 28)
pylab.imshow(im)
pylab.show()
2.3 多层神经元 二层
# -*- coding: utf-8 -*-
import tensorflow as tf
# 导入 MINST 数据集
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# 参数设置
learning_rate = 0.001
training_epochs = 50
batch_size = 100
display_step = 1
# Network Parameters
n_hidden_1 = 256 # 1st layer number of features
n_hidden_2 = 256 # 2nd layer number of features
n_input = 784 # MNIST data 输入 (img shape: 28*28)
n_classes = 10 # MNIST 列别 (0-9 ，一共10类)
# 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):
# Hidden layer with RELU activation
layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
layer_1 = tf.nn.relu(layer_1)
# Hidden layer with RELU activation
layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
layer_2 = tf.nn.relu(layer_2)
# Output layer with linear activation
out_layer = tf.matmul(layer_2, weights['out']) + biases['out']
return out_layer
# 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]))
}
# 构建模型
pred = multilayer_perceptron(x, weights, biases)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# 初始化变量
init = tf.global_variables_initializer()
# 启动session
with tf.Session() as sess:
sess.run(init)
# 启动循环开始训练
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = int(mnist.train.num_examples / batch_size)
# 遍历全部数据集
for i in range(total_batch):
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop) and cost op (to get loss value)
_, c = sess.run([optimizer, cost], feed_dict={
x: batch_x,
y: batch_y})
# Compute average loss
avg_cost += c / total_batch
# 显示训练中的详细信息
if epoch % display_step == 0:
print("Epoch:", '%04d' % (epoch + 1), "cost=",
"{:.9f}".format(avg_cost))
print(" Finished!")
# 测试 model
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
# 计算准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print("Accuracy:", accuracy.eval({
x: mnist.test.images, y: mnist.test.labels}))
2.4 多层神经元 三层
# -*- coding: utf-8 -*-
import pylab
import tensorflow as tf
# 导入 MINST 数据集
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# 参数设置
learning_rate = 0.001
training_epochs = 50
batch_size = 100
display_step = 1
# Network Parameters
n_hidden_1 = 512 # 1st layer number of features
n_hidden_2 = 256 # 2nd layer number of features
n_hidden_3 = 64 # 3nd layer number of features
n_input = 784 # MNIST data 输入 (img shape: 28*28)
n_classes = 10 # MNIST 列别 (0-9 ，一共10类)
# 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):
# Hidden layer with RELU activation
layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
layer_1 = tf.nn.relu(layer_1)
# Hidden layer with RELU activation
layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
layer_2 = tf.nn.relu(layer_2)
# Hidden layer with RELU activation
layer_3 = tf.add(tf.matmul(layer_2, weights['h3']), biases['b3'])
layer_3 = tf.nn.relu(layer_3)
# Output layer with linear activation
out_layer = tf.matmul(layer_3, weights['out']) + biases['out']
return out_layer
# 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])),
'h3': tf.Variable(tf.random_normal([n_hidden_2, n_hidden_3])),
'out': tf.Variable(tf.random_normal([n_hidden_3, n_classes]))
}
biases = {
'b1': tf.Variable(tf.random_normal([n_hidden_1])),
'b2': tf.Variable(tf.random_normal([n_hidden_2])),
'b3': tf.Variable(tf.random_normal([n_hidden_3])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
# 构建模型
pred = multilayer_perceptron(x, weights, biases)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# 初始化变量
init = tf.global_variables_initializer()
saver = tf.train.Saver()
model_path = "log4/Date.ckpt"
# 启动session
with tf.Session() as sess:
sess.run(init)
# 启动循环开始训练
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = int(mnist.train.num_examples / batch_size)
# 遍历全部数据集
for i in range(total_batch):
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop) and cost op (to get loss value)
_, c = sess.run([optimizer, cost], feed_dict={
x: batch_x,
y: batch_y})
# Compute average loss
avg_cost += c / total_batch
# 显示训练中的详细信息
if epoch % display_step == 0:
print("Epoch:", '%04d' % (epoch + 1), "cost=",
"{:.9f}".format(avg_cost))
print(" Finished!")
# Save model weights to disk
save_path = saver.save(sess, model_path)
print("Model saved in file: %s" % save_path)
# 读取模型
print("Starting 2nd session...")
with tf.Session() as sess:
# Initialize variables
sess.run(tf.global_variables_initializer()) # 初始化模型
# Restore model weights from previously saved model
saver.restore(sess, model_path) # 恢复模型
# 测试 model
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
# 计算准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print("模型四准确率:", accuracy.eval({
x: mnist.test.images, y: mnist.test.labels}))
output = tf.argmax(pred, 1)
batch_xs, batch_ys = mnist.train.next_batch(2)
outputval, predv = sess.run([output, pred], feed_dict={
x: batch_xs})
print(outputval, batch_ys)
im = batch_xs[0]
im = im.reshape(-1, 28)
pylab.imshow(im)
pylab.show()
im = batch_xs[1]
im = im.reshape(-1, 28)
pylab.imshow(im)
pylab.show()
3.1 模型结果
| 网络类型 | LOSS | Accuracy |
|---|---|---|
| 单神经元 | 0.292795215 | 0.9145 |
| 单神经元+MAXOUT | 0.155645897 | 0.9469 |
| 多层神经元 二层 | 0.145589752 | 0.9647 |
| 多层神经元 三层 | 0.582389482 | 0.9656 |
3.2 结论
由普通线性单神经元训练出的结果并不是最优解，经过Maxout强化其特征后能够优化一部分样本和训练的结果，但也存在一定问题，而使用全连接网络得出的结果相较于单神经元的线性网络更优，但对于这个数据集，二层网络和三层网络并没有显著的区别，三层网络训练的耗时更多。