TensorFlow MNIST for Experts 精度低

Question

我已经按照 tensorflow MNIST for Experts 的教程学习了。我编写了如下代码，它是本教程的副本。但是，当我运行我的代码时，准确率只有 92%、86%、...它运行非常快，在我的 mac 上只需要 1 或 2 分钟。并且随着步长的增加，accuracy

step 0, training accuracy 0.08
step 100, training accuracy 0.1
step 200, training accuracy 0.16
step 300, training accuracy 0.22
step 400, training accuracy 0.1
step 500, training accuracy 0.18
step 600, training accuracy 0.26
step 700, training accuracy 0.16
step 800, training accuracy 0.24
...
step 19600, training accuracy 0.9
step 19700, training accuracy 0.82
step 19800, training accuracy 0.98
step 19900, training accuracy 0.86
test accuracy 0.9065

但是当我运行官方代码mnist_deep.py。它运行非常缓慢，输出为

step 0, training accuracy 0.1
step 100, training accuracy 0.84
step 200, training accuracy 0.84
step 300, training accuracy 0.9
step 400, training accuracy 0.88
step 500, training accuracy 0.92
step 600, training accuracy 0.98
step 700, training accuracy 0.96
step 800, training accuracy 0.96
step 900, training accuracy 0.96
step 1000, training accuracy 0.96
step 1100, training accuracy 0.94
step 1200, training accuracy 0.96

效果很好。我比较我的代码和 mnist_deep.py。唯一的区别是它们使用 with 。为什么我的代码运行如此糟糕？为什么他们应该使用 with ？下面是我的代码。

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

from tensorflow.examples.tutorials.mnist import input_data

import tensorflow as tf

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')

def main(_):
    mnist = input_data.read_data_sets("/MNIST_data/", one_hot=True)

    x = tf.placeholder(tf.float32, [None, 784])
    y_ = tf.placeholder(tf.float32, [None, 10])

    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(tf.float32)
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

    W_fc2 = weight_variable([1024, 10])
    b_fc2 = bias_variable([10])
    y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

    cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=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, tf.float32))

    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        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}))

if __name__ == '__main__':
    tf.app.run(main=main)

Answer 1

您已将 train_step.run 调用放入 if i % 100 == 0: 块中。

TensorFlow MNIST for Experts 精度低

TensorFlow MNIST for Experts low accuracy

python

mnist

tensorflow