环境：ubuntu16.04+tensorflow+cpu
1、训练的时候分批，测试的时候一次性测试，占用显存较大
import tensorflow as tf
import tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) #
x = tf.placeholder(tf.float32, [None, 784]) #
y_actual = tf.placeholder(tf.float32, shape=[None, 10]) #
#
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(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')
#
x_image = tf.reshape(x, [-1,28,28,1]) #
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) #28*28*32
h_pool1 = max_pool(h_conv1) #14*14*32
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) #14*14*64
h_pool2 = max_pool(h_conv2) #7*7*64
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) #
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) #
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_predict=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) #
###
cross_entropy = -tf.reduce_sum(y_actual*tf.log(y_predict)) #
train_step = tf.train.GradientDescentOptimizer(1e-3).minimize(cross_entropy) #
correct_prediction = tf.equal(tf.argmax(y_predict,1), tf.argmax(y_actual,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) #
sess=tf.InteractiveSession()
sess.run(tf.initialize_all_variables())
for i in range(20000):
batch = mnist.train.next_batch(50)
if i%100 == 0: #
train_acc = accuracy.eval(feed_dict={x:batch[0], y_actual: batch[1], keep_prob: 1.0})
print 'step %d, training accuracy %g'%(i,train_acc)
train_step.run(feed_dict={x: batch[0], y_actual: batch[1], keep_prob: 0.5})
test_acc=accuracy.eval(feed_dict={x: mnist.test.images, y_actual: mnist.test.labels, keep_prob: 1.0})
print "test accuracy %g"%test_acc
#print ("test accuracy ",test_acc)
2、测试的时候也可以设置较小的batch来看准确率
import tensorflow as tf
import tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) #
x = tf.placeholder(tf.float32, [None, 784]) #
y_actual = tf.placeholder(tf.float32, shape=[None, 10]) #
#
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(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')
#
x_image = tf.reshape(x, [-1,28,28,1]) #
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) #28*28*32
h_pool1 = max_pool(h_conv1) #14*14*32
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) #14*14*64
h_pool2 = max_pool(h_conv2) #7*7*64
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) #
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) #
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) #
# 1.损失函数：cross_entropy
cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))
# 2.优化函数：AdamOptimizer
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
# 3.预测准确结果统计
# 预测值中最大值（１）即分类结果，是否等于原始标签中的（１）的位置。argmax()取最大值所在的下标
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.arg_max(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# 如果一次性来做测试的话，可能占用的显存会比较多，所以测试的时候也可以设置较小的batch来看准确率
test_acc_sum = tf.Variable(0.0)
batch_acc = tf.placeholder(tf.float32)
new_test_acc_sum = tf.add(test_acc_sum, batch_acc)
update = tf.assign(test_acc_sum, new_test_acc_sum)
# 定义了变量必须要初始化，或者下面形式
sess.run(tf.global_variables_initializer())
# 或者某个变量单独初始化 如：
# x.initializer.run()
# 训练
for i in range(5000):
X_batch, y_batch = mnist.train.next_batch(batch_size=50)
if i % 500 == 0:
train_accuracy = accuracy.eval(feed_dict={X_: X_batch, y_: y_batch, keep_prob: 1.0})
print "step %d, training acc %g" % (i, train_accuracy)
train_step.run(feed_dict={X_: X_batch, y_: y_batch, keep_prob: 0.5})
# 全部训练完了再做测试，batch_size=100
for i in range(100):
X_batch, y_batch = mnist.test.next_batch(batch_size=100)
test_acc = accuracy.eval(feed_dict={X_: X_batch, y_: y_batch, keep_prob: 1.0})
update.eval(feed_dict={batch_acc: test_acc})
if (i+1) % 20 == 0:
print "testing step %d, test_acc_sum %g" % (i+1, test_acc_sum.eval())
print " test_accuracy %g" % (test_acc_sum.eval() / 100.0)3、查看中间层的结果--这一个程序不能单独运行，与上面的放到一个程序里
#!/usr/bin/python
#-*-coding:utf-8 -*-
import matplotlib.pyplot as plt #
#import sys
#reload(sys)
#sys.setdefaultencoding('utf8')
#
import tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
img1 = mnist.train.images[1]
label1 = mnist.train.labels[1]
print label1 # 所以这个是数字 6 的图片
print 'img_data shape =', img1.shape
# 我们需要把它转为 28 * 28 的矩阵
img1.shape = [28, 28]
print img1.shape
plt.imshow(img1)
plt.axis('off') # 不显示坐标轴
plt.show()
# 我们可以通过设置 cmap 参数来显示灰度图
plt.imshow(img1, cmap='gray') # 'hot' 是热度图
plt.show()
#####################################
#查看中间结果
# 首先应该把 img1 转为正确的shape (None, 784)
X_img = img1.reshape([-1, 784])
y_img = mnist.train.labels[1].reshape([-1, 10])
# 我们要看 Conv1 的结果，即 h_conv1
result = h_conv1.eval(feed_dict={X_: X_img, y_: y_img, keep_prob: 1.0})
print result.shape
print type(result)
for _ in xrange(32):
show_img = result[:,:,:,_]
show_img.shape = [28, 28]
plt.subplot(4, 8, _ + 1)
plt.imshow(show_img, cmap='gray')
plt.axis('off')
plt.show()