Python tensorflow内存MNIST教程

我正试图从中完成MNIST教程 我有2gb geforce 760gtx，每次都会耗尽内存。 我已尝试在脚本末尾的代码行中减少批处理大小：

for i in range(20000):
batch = mnist.train.next_batch(5)
if i%100 == 0:
    train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
    print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

但它总是尝试使用相同数量的ram。我是tensorflow的新手，我想问一下，在这个例子中，我在哪里可以减少内存的使用，或者是否有一个代码可以将它推送到CPU上

完整代码：

# Load mnist data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

# Start TensorFlow InteractiveSession
import tensorflow as tf
sess = tf.InteractiveSession()

# Build a Softmax Regression Model

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

# 2. Variables
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
sess.run(tf.initialize_all_variables())

# 3. Predicted Class and Loss Function
y = tf.matmul(x,W) + b
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y, y_))

# Train the Model
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
for i in range(1000):
    batch = mnist.train.next_batch(100)
    train_step.run(feed_dict={x: batch[0], y_: batch[1]})

# Evaluate the Model
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))

# Build a Multilayer Convolutional Network
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)

# Convolutional and Pooling
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')

# First Convolutional Layer
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)

# Second Convolutional Layer
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)

# Densely Connected Layer
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)

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

# Readout Layer
W_fc2 = weight_variable([1024,10])
b_fc2 = bias_variable([10])

y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

# Train and Evaluate the Model
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.run(tf.initialize_all_variables())
for i in range(20000):
    batch = mnist.train.next_batch(5)
    if i%100 == 0:
        train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
    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}))

---

我预计问题不会发生在训练循环中，而是在最终的精度评估中，在一批10000张图像中通过了所有测试集：

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

在2GB或更低的GPU上，这足以耗尽所有可用内存。我的GTX 965M也有同样的问题

解决方案是使用批次进行评估。您需要计算批次总数并累计总精度。代码：

# evaluate in batches to avoid out-of-memory issues
n_batches = mnist.test.images.shape[0] // 50
cumulative_accuracy = 0.0
for index in range(n_batches):
    batch = mnist.test.next_batch(50)
    cumulative_accuracy += accuracy.eval(
        feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
print("test accuracy {}".format(cumulative_accuracy / n_batches))

---

您可以在此处找到MNIST数据集的已解码版本：