def get_random_cached_bottlenecks()

in machine-learning-notebooks/02-mobilenet-transfer-learning-scripts/retrain.py [0:0]

• 40 lines of code
• 5 McCabe index (conditional complexity)

def get_random_cached_bottlenecks(sess, image_lists, how_many, category,
                                  bottleneck_dir, image_dir, jpeg_data_tensor,
                                  decoded_image_tensor, resized_input_tensor,
                                  bottleneck_tensor, architecture):
  """Retrieves bottleneck values for cached images.

  If no distortions are being applied, this function can retrieve the cached
  bottleneck values directly from disk for images. It picks a random set of
  images from the specified category.

  Args:
    sess: Current TensorFlow Session.
    image_lists: Dictionary of training images for each label.
    how_many: If positive, a random sample of this size will be chosen.
    If negative, all bottlenecks will be retrieved.
    category: Name string of which set to pull from - training, testing, or
    validation.
    bottleneck_dir: Folder string holding cached files of bottleneck values.
    image_dir: Root folder string of the subfolders containing the training
    images.
    jpeg_data_tensor: The layer to feed jpeg image data into.
    decoded_image_tensor: The output of decoding and resizing the image.
    resized_input_tensor: The input node of the recognition graph.
    bottleneck_tensor: The bottleneck output layer of the CNN graph.
    architecture: The name of the model architecture.

  Returns:
    List of bottleneck arrays, their corresponding ground truths, and the
    relevant filenames.
  """
  class_count = len(image_lists.keys())
  bottlenecks = []
  ground_truths = []
  filenames = []
  if how_many >= 0:
    # Retrieve a random sample of bottlenecks.
    for unused_i in range(how_many):
      label_index = random.randrange(class_count)
      label_name = list(image_lists.keys())[label_index]
      image_index = random.randrange(MAX_NUM_IMAGES_PER_CLASS + 1)
      image_name = get_image_path(image_lists, label_name, image_index,
                                  image_dir, category)
      bottleneck = get_or_create_bottleneck(
          sess, image_lists, label_name, image_index, image_dir, category,
          bottleneck_dir, jpeg_data_tensor, decoded_image_tensor,
          resized_input_tensor, bottleneck_tensor, architecture)
      ground_truth = np.zeros(class_count, dtype=np.float32)
      ground_truth[label_index] = 1.0
      bottlenecks.append(bottleneck)
      ground_truths.append(ground_truth)
      filenames.append(image_name)
  else:
    # Retrieve all bottlenecks.
    for label_index, label_name in enumerate(image_lists.keys()):
      for image_index, image_name in enumerate(
          image_lists[label_name][category]):
        image_name = get_image_path(image_lists, label_name, image_index,
                                    image_dir, category)
        bottleneck = get_or_create_bottleneck(
            sess, image_lists, label_name, image_index, image_dir, category,
            bottleneck_dir, jpeg_data_tensor, decoded_image_tensor,
            resized_input_tensor, bottleneck_tensor, architecture)
        ground_truth = np.zeros(class_count, dtype=np.float32)
        ground_truth[label_index] = 1.0
        bottlenecks.append(bottleneck)
        ground_truths.append(ground_truth)
        filenames.append(image_name)
  return bottlenecks, ground_truths, filenames