Question

我尝试在TensorFlow中创建一个简单的卷积神经网络。当我在下面运行我的代码时，一切似乎都很好。我在Spyder IDE中运行它并监视内存使用情况 - 它在我的笔记本电脑上增长到64-65％而不再进一步。

batch_size = 16
patch_size = 5
depth = 16
num_hidden = 64

graph = tf.Graph()

with graph.as_default():

  # Input data.
  tf_train_dataset = tf.placeholder(
    tf.float32, shape=(batch_size, image_size, image_size, num_channels))
  tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))
  tf_valid_dataset = tf.constant(valid_dataset)
  tf_test_dataset = tf.constant(test_dataset)

  # Variables.
  layer1_weights = tf.Variable(tf.truncated_normal(
      [patch_size, patch_size, num_channels, depth], stddev=0.1))
  layer1_biases = tf.Variable(tf.zeros([depth]))
  layer2_weights = tf.Variable(tf.truncated_normal(
      [patch_size, patch_size, depth, depth], stddev=0.1))
  layer2_biases = tf.Variable(tf.constant(1.0, shape=[depth]))
  layer3_weights = tf.Variable(tf.truncated_normal(
      [image_size // 4 * image_size // 4 * depth, num_hidden], stddev=0.1))
  layer3_biases = tf.Variable(tf.constant(1.0, shape=[num_hidden]))
  layer4_weights = tf.Variable(tf.truncated_normal(
      [num_hidden, num_labels], stddev=0.1))
  layer4_biases = tf.Variable(tf.constant(1.0, shape=[num_labels]))

  # Model.
  #Now instead of using strides = 2 for convolutions we will use maxpooling with
  #same convolution sizes
  def model(data):
    conv = tf.nn.conv2d(data, layer1_weights, [1, 2, 2, 1], padding='SAME')
    hidden = tf.nn.relu(conv + layer1_biases)
    conv = tf.nn.conv2d(hidden, layer2_weights, [1, 2, 2, 1], padding='SAME')
    hidden = tf.nn.relu(conv + layer2_biases)
    shape = hidden.get_shape().as_list()
    reshape = tf.reshape(hidden, [shape[0], shape[1] * shape[2] * shape[3]])
    hidden = tf.nn.relu(tf.matmul(reshape, layer3_weights) + layer3_biases)
    return tf.matmul(hidden, layer4_weights) + layer4_biases

  # Training computation.
  logits = model(tf_train_dataset)
  loss = tf.reduce_mean(
    tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))

  # Optimizer.
  optimizer = tf.train.GradientDescentOptimizer(0.05).minimize(loss)

  # Predictions for the training, validation, and test data.
  train_prediction = tf.nn.softmax(logits)
  valid_prediction = tf.nn.softmax(model(tf_valid_dataset))
  test_prediction = tf.nn.softmax(model(tf_test_dataset))

num_steps = 1001

with tf.Session(graph=graph) as session:
  tf.initialize_all_variables().run()
  print('Initialized')
  for step in range(num_steps):
    offset = (step * batch_size) % (train_labels.shape[0] - batch_size)
    batch_data = train_dataset[offset:(offset + batch_size), :, :, :]
    batch_labels = train_labels[offset:(offset + batch_size), :]
    feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels}
    _, l, predictions = session.run(
      [optimizer, loss, train_prediction], feed_dict=feed_dict)
    if (step % 50 == 0):
      print('Minibatch loss at step %d: %f' % (step, l))
      print('Minibatch accuracy: %.1f%%' % accuracy(predictions, batch_labels))
      print('Validation accuracy: %.1f%%' % accuracy(
        valid_prediction.eval(), valid_labels))
  print('Test accuracy: %.1f%%' % accuracy(test_prediction.eval(), test_labels))

好的，之后我尝试引入内核为2的maxpooling，并使用maxpooling而不是conv层来减小数据的大小。它看起来如下：

conv = tf.nn.conv2d(data, layer1_weights, [1, 1, 1, 1], padding='SAME')
    maxpool = tf.nn.max_pool(conv, [1, 2, 2, 1], [1, 2, 2, 1], padding='SAME')
    hidden = tf.nn.relu(maxpool + layer1_biases)
    conv = tf.nn.conv2d(hidden, layer2_weights, [1, 2, 2, 1], padding='SAME')

其他一切都保持不变。但是当我这样做时（注意，我只引入了一个maxpooling层），内存使用率增长到100％，而我的iPython内核就死了。任何关于这种奇怪行为的想法，为什么内存使用量如此之大？难道我做错了什么？关于如何减少内存使用量的任何建议？

Answer 1

假设您在单通道6x6输入上使用一个3x3滤波器。

当您对步幅2进行跨步卷积时，会产生3x3的结果。

如此有效地使用输入36单位+过滤9单位+输出9单位内存。

现在，当您尝试在无条件卷积后应用最大池时，您的卷积层会产生6x6输出，您可以在其上应用maxpool以获得3x3输出。请注意，在应用max pool之前，我们有一个大小为6x6的中间结果。

所以在这里使用输入36单位+过滤9单位+中间结果36单位+输出9单位内存

这可以解释内存使用情况。这不是一种奇怪的行为。至于为什么它完全耗尽你的资源取决于你的图像大小，批量大小和你正在使用的过滤器数量。

TensorFlow - nn.max_pooling极大地增加了内存使用量

1 个答案: