tensorflow 入门学习(2)

Mnist数据集获取

这里有input_data.py,但是我们下载不到，被墙了，所以从其他途径下好那四个压缩包，然后修改一下这里面的代码就可以像中文社区里的教程那样用

import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

# local_file = maybe_download(TRAIN_IMAGES, train_dir)
train_images = extract_images('MNIST/train-images-idx3-ubyte.gz')
# local_file = maybe_download(TRAIN_LABELS, train_dir)
train_labels = extract_labels('MNIST/train-labels-idx1-ubyte.gz', one_hot=one_hot)
# local_file = maybe_download(TEST_IMAGES, train_dir)
test_images = extract_images('MNIST/t10k-images-idx3-ubyte.gz')
# local_file = maybe_download(TEST_LABELS, train_dir)
test_labels = extract_labels('MNIST/t10k-labels-idx1-ubyte.gz', one_hot=one_hot)

把这几行修改成不用 下载，并且直接解压已经下载好的数据集，路径改成自己下载的路径即可

然后是运行一下多层神经网络的mnist代码

import tensorflow as tf
import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

#single softMax layer
# x = tf.placeholder("float", [None, 784])
# W = tf.Variable(tf.zeros([784,10]))
# b = tf.Variable(tf.zeros([10]))
# y = tf.nn.softmax(tf.matmul(x,W) + b)

# y_ = tf.placeholder("float", [None,10])
# cross_entropy = -tf.reduce_sum(y_*tf.log(y))
# train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
# init = tf.initialize_all_variables()
# sess = tf.Session()
# sess.run(init)
# for i in range(1000):
#   batch_xs, batch_ys = mnist.train.next_batch(100)
#   sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

# correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
# accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
# print sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels})

sess = tf.InteractiveSession()

def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)

def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)

def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')

#the first layer  可以理解卷积为生成了32副新的图像，现在数量是28*28*32
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

x = tf.placeholder("float", [None, 784])
x_image = tf.reshape(x, [-1,28,28,1])

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)  #一次池化，现在数量为14*14*32

#the second layer  现在对上面的32副图像每一副再生成64张图像，现在规模14*14*64，注意每一个卷积核处理32个通道，然后对32个通道进行累加之后再取激活函数值得到一个通道
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2) #再次池化，规模为7*7*64

# all-connection layer #对64个通道副图像做全连接，输出1024个激励值
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

#dropout
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

#the output layer #对1024的向量再变成进行10维，代表十个数字
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

y_ = tf.placeholder("float", [None,10])

cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

sess.run(tf.initialize_all_variables())
for i in range(20000):
batch = mnist.train.next_batch(50)
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={
x:batch[0], y_: batch[1], keep_prob: 1.0})
print "step %d, training accuracy %g"%(i, train_accuracy)
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

print "test accuracy %g"%accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})

tf.cast将bool值转化成float，然后reduce_mean计算均值

第二版修改：将模型训练和测试分开了，测试了模型的存储和调用模型

import tensorflow as tf
import input_data mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)

def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)

def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')

#the first layer
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

x = tf.placeholder("float", [None, 784])
x_image = tf.reshape(x, [-1,28,28,1])

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

#the second layer
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

# all-connection layer
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

#dropout
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

#the output layer
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

y_ = tf.placeholder("float", [None,10])

cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

#sess = tf.InteractiveSession()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(10000):
batch = mnist.train.next_batch(50)
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={
x:batch[0], y_: batch[1], keep_prob: 1.0})
print "step %d, training accuracy %g"%(i, train_accuracy)
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

all_saver = tf.train.Saver()
all_saver.save(sess,"save/mnist_model.ckpt")
# batch = mnist.test.next_batch(500)
# print "test accuracy %g"%accuracy.eval(feed_dict={
# #x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})
# x: batch[0], y_: batch[1], keep_prob: 1.0})

test.py 但是这里有一个问题就是这样只能把模型重新写一遍，其实应该是不用的，暂时不知道怎么写
import tensorflow as tf
import input_data mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)

def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)

def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')

#the first layer
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

x = tf.placeholder("float", [None, 784])
x_image = tf.reshape(x, [-1,28,28,1])

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

#the second layer
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

# all-connection layer
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

#dropout
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.d
4000
ropout(h_fc1, keep_prob)

#the output layer
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

y_ = tf.placeholder("float", [None,10])

cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

saver = tf.train.Saver()
# saver = tf.train.import_meta_graph("save/mnist_model.ckpt.meta")
with tf.Session() as sess:
saver.restore(sess, "save/mnist_model.ckpt")
batch = mnist.test.next_batch(1000)
print "test accuracy %g"%accuracy.eval(feed_dict={
#x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})
x: batch[0], y_: batch[1], keep_prob: 1.0})结果准确率在0.988