# below is mnist for ml beginners
import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
import tensorflow as tf
sess = tf.InteractiveSession()
x = tf.placeholder("float",shape=[None, 784])
y_ = tf.placeholder("float",shape = [None,10])
# x is input, y_ is the result
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
sess.run(tf.initialize_all_variables())
# initialize all variables
y = tf.nn.softmax(tf.matmul(x,W)+b)
# softmax 只是一个压缩数值的函数,没有计算交叉商损失
# N*10 * N*10 这里是点乘,而不是矩阵乘法
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
# 计算出来了所有的交叉熵
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
for i in range(1000):
batch = mnist.train.next_batch(50)
train_step.run(feed_dict= {x:batch[0], y_: batch[1]})
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels})
#====================================================================
# below is mnist for experts
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')
#第二个参数ksize:池化窗口的大小,取一个四维向量,一般是[1, height, width, 1],因为我们不想在batch和channels上做池化,所以这两个维度设为了1
#第三个参数strides:和卷积类似,窗口在每一个维度上滑动的步长,一般也是[1, stride,stride, 1]
#http://blog.csdn.net/mao_xiao_feng/article/details/53444333
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
# -1 代表第一个参数由 N/28/28/1 决定
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)
# 不太清楚64个 feature map 到底能干什么。?
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)
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
#为什么图片尺寸减小到了7*7 ? 因为padding 的参数为 SAME
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)
# 现在 h_fc1 的大小为 N × 1024 什么用?
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)
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})
这样 mnist 暂且告一段落。