TensorFlow入门——MNIST深入

#load MNIST data
import tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets("MNIST_data/",one_hot=True)

#start tensorflow interactiveSession
import tensorflow as tf
sess = tf.InteractiveSession()

#weight initilization
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)

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

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

#Create the model
#placeholder
x = tf.placeholder("float",[None, 784])
y_ = tf.placeholder("float", [None, 10])

#variable
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))

y = tf.nn.softmax(tf.matmul(x,W) +b)

#first convolutional layer
w_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])

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)

#second convolutional 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)

#densely connected 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)

#readout 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)

#train and evaluate the model
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
#train_step = tf.train.AdagradOptimizer(1e-4).minimize(cross_entropy)
train_step = tf.train.GradientDescentOptimizer(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(5000):
    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, train 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(fedd_dict={x:mnist.test.images, y_:mnist.test.labels, keep_prob:1.0})

 同样是极客学院的课程，其实也是翻译的国外的robot-ai博客上的内容，但是这个博客，现在打不开了，可能是墙的问题？没有太深究。

按照作者的说法，是采用自适应下降的方式，在train阶段能达到99%的正确率，但是，我的结果只有93%左右，修改梯度步长到1e-4也只有94% 。因此尝试换用原来的梯度下降方式，反而能获得97.61%的正确率，在训练中还达到过98%，这个问题比较无奈，修改步长的结果提升也并不明显。有人在评论中说在不同的平台上测试的值不同，比如在纯CPU环境，和我的结果比较相似。在K20环境中能达到99%，这个问题留待以后探索。代码参考至：文章链接： http://blog.csdn.net/yhl_leo/article/details/50624471