TensorFlow。运行 cifar10_train.py 时未反映 CIFAR10 示例中的代码更改答案

【问题标题】：TensorFlow. Changes in code in CIFAR10 example are not reflected when I run cifar10_train.pyTensorFlow。运行 cifar10_train.py 时未反映 CIFAR10 示例中的代码更改
【发布时间】：2016-01-14 03:26:25
【问题描述】：

例如，我想更改 distorted_inputs 中的失真。我注释掉了随机裁剪和随机翻转。这样做之后，我保存了文件，并运行了 cifar10_train.py。然后我运行 TensorBoard，并在图像可视化器中查看图像。我意识到它们仍然被翻转和裁剪。这很奇怪，因为我已经编辑了代码，所以它不应该发生。有什么修复吗？

def distorted_inputs(data_dir, batch_size):
  """Construct distorted input for CIFAR training using the Reader ops.

  Args:
    data_dir: Path to the CIFAR-10 data directory.
    batch_size: Number of images per batch.

  Returns:
    images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
    labels: Labels. 1D tensor of [batch_size] size.
  """
  filenames = [os.path.join(data_dir, 'data_batch_%d.bin' % i)
               for i in xrange(1, 6)]
  for f in filenames:
    if not gfile.Exists(f):
      raise ValueError('Failed to find file: ' + f)

  # Create a queue that produces the filenames to read.
  filename_queue = tf.train.string_input_producer(filenames)

  # Read examples from files in the filename queue.
  read_input = read_cifar10(filename_queue)
  reshaped_image = tf.cast(read_input.uint8image, tf.float32)
  distorted_image = reshaped_image

  height = IMAGE_SIZE
  width = IMAGE_SIZE

  # Image processing for training the network. Note the many random
  # distortions applied to the image.

  # Randomly crop a [height, width] section of the image.
  # distorted_image = tf.image.random_crop(reshaped_image, [height, width])

  # Randomly flip the image horizontally.
  # distorted_image = tf.image.random_flip_left_right(distorted_image)

  # Because these operations are not commutative, consider randomizing
  # randomize the order their operation.
  distorted_image = tf.image.random_brightness(distorted_image,
                                               max_delta=63)
  distorted_image = tf.image.random_contrast(distorted_image,
                                             lower=0.2, upper=1.8)

  # Subtract off the mean and divide by the variance of the pixels.
  float_image = tf.image.per_image_whitening(distorted_image)

  # Ensure that the random shuffling has good mixing properties.
  min_fraction_of_examples_in_queue = 0.4
  min_queue_examples = int(NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN *
                           min_fraction_of_examples_in_queue)
  print ('Filling queue with %d CIFAR images before starting to train. '
         'This will take a few minutes.' % min_queue_examples)

  # Generate a batch of images and labels by building up a queue of examples.
  return _generate_image_and_label_batch(float_image, read_input.label,
                                         min_queue_examples, batch_size)

【问题讨论】：

标签： tensorflow

【解决方案1】：

我发现了问题。更改每个 .py 文件顶部的行，例如：

from tensorflow.models.image.cifar10 import cifar10

到

import cifar10

成功了。我不太确定它为什么会起作用，但这可能是因为执行这样的导入会进入 python dist-packages。期待确切知道这是如何工作的人的回答！

【讨论】：