深入MNIST code测试

本系列文章由 @yhl_leo 出品，转载请注明出处。
文章链接： http://blog.csdn.net/yhl_leo/article/details/50624471

---

依照教程：深入MNIST教程和Deep MNIST for Experts（英文官网），测试代码及结果如下：

# load MNIST dataimport input_datamnist = input_data.read_data_sets("Mnist_data/", one_hot=True)# start tensorflow interactiveSessionimport tensorflow as tfsess = tf.InteractiveSession()# weight initializationdef 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)# convolutiondef conv2d(x, W):    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')# poolingdef 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# placeholderx = tf.placeholder("float", [None, 784])y_ = tf.placeholder("float", [None, 10])# variablesW = tf.Variable(tf.zeros([784,10]))b = tf.Variable(tf.zeros([10]))y = tf.nn.softmax(tf.matmul(x,W) + b)# first convolutinal layerw_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 layerw_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 layerw_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)# dropoutkeep_prob = tf.placeholder("float")h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)# readout layerw_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 modelcross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))train_step = tf.train.AdagradOptimizer(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, 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(feed_dict={x:mnist.test.images, y_:mnist.test.labels, keep_prob:1.0})

其中各个操作的含义，文档里讲解的比较清楚，就不累述了，结果截图：

可以看出，训练结果准确率为93.22%，并不是教程里说的99.2%～

（有读者提议将步长修改更小，测试后效果仍然不佳）

将上述代码中，训练优化方法修改为梯度下降算法：

#train_step = tf.train.AdagradOptimizer(1e-4).minimize(cross_entropy)train_step = tf.train.GradientDescentOptimizer(1e-3).minimize(cross_entropy)
1
2
1
2

训练结果精度为：99.25%与教程中的结果一致。