Question

我一直在关注tensorflow教程。我导入了MNIST数据集并运行了2层卷积神经网络的代码。训练需要将近45分钟。我想通过丢弃一些数据来减少训练数据。我怎么做？这是代码：

import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

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')

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


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)

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(y_conv, y_))
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))
sess = tf.Session()
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(session=sess,feed_dict={x:batch[0], y_: batch[1], keep_prob: 1.0})
    print("step %d, training accuracy %g"%(i, train_accuracy))
  train_step.run(session=sess,feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

print("test accuracy %g"%accuracy.eval(session=sess,feed_dict={x: np.split(mnist.test.images,5)[0], y_: np.split(mnist.test.labels,5)[0], keep_prob: 1.0}))

我减少了测试数据的大小，因为它是一个numpy数组。如何训练数据？

Answer 1

您正在使用https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/learn/python/learn/datasets/mnist.py

中定义的数据集提供程序

要减少训练样本的数量，您可以更改此文件（第237行），或创建修改后的版本并使用它，而不是

from tensorflow.examples.tutorials.mnist import input_data

哪个指向我上面提到的链接。

Answer 2

削减您的训练样本对您没有任何好处 - 只要您使用小型飞机，它不会直接影响性能。作为更好的选择，您可以减少时期数量和/或提高学习率。在这种情况下，减少数据样本是个坏主意

Answer 3

只有一个问题 - 我们正在谈论这段代码`https://www.tensorflow.org/tutorials/mnist/pros/ ???

所以如果这需要45分钟，我猜你在cpu上运行 - 你应该考虑使用gpu。我在Azure VM N系列中使用Tesla K 80 GPU测试了代码，并在4分钟内完成

拆分MNIST数据张量流

3 个答案: