mnist 卷积网络精度不好

Question

我是 TensorFlow 中的 tiro。我只是从 Tensorflow 教程开始（link）。我尝试在教程中描述的卷积网络中构建 mnist 训练。但是经过编码，以及几次调试。我仍然无法获得正常的准确性。代码如下。

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, shape = [None, 784])
y_ = 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_2x2(x):
    return tf.nn.max_pool(x, ksize = [1,2,2,1], strides = [1,2,2,1],
                    padding = 'SAME')

#import input_data
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)
h_pool1 = max_pool_2x2(h_conv1)

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])

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)


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

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

我不知道这段代码有什么问题，我搜索了其他的代码，几乎没有什么不同。但是我的准确率真的很差，0.11左右。 :(请帮帮我！谢谢~

Answer 1

你在计算 cross_entropy(loss) 时犯了错误

改变这一行

cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))

到这里

cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1]))

编辑：

你也应该正确缩进这一行

sess.run(train_step, feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

正确的缩进是

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