in machine-learning-notebooks/02-mobilenet-transfer-learning-scripts/retrain.py [0:0]
def get_or_create_bottleneck(sess, image_lists, label_name, index, image_dir,
category, bottleneck_dir, jpeg_data_tensor,
decoded_image_tensor, resized_input_tensor,
bottleneck_tensor, architecture):
"""Retrieves or calculates bottleneck values for an image.
If a cached version of the bottleneck data exists on-disk, return that,
otherwise calculate the data and save it to disk for future use.
Args:
sess: The current active TensorFlow Session.
image_lists: Dictionary of training images for each label.
label_name: Label string we want to get an image for.
index: Integer offset of the image we want. This will be modulo-ed by the
available number of images for the label, so it can be arbitrarily large.
image_dir: Root folder string of the subfolders containing the training
images.
category: Name string of which set to pull images from - training, testing,
or validation.
bottleneck_dir: Folder string holding cached files of bottleneck values.
jpeg_data_tensor: The tensor to feed loaded jpeg 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 output tensor for the bottleneck values.
architecture: The name of the model architecture.
Returns:
Numpy array of values produced by the bottleneck layer for the image.
"""
label_lists = image_lists[label_name]
sub_dir = label_lists['dir']
sub_dir_path = os.path.join(bottleneck_dir, sub_dir)
ensure_dir_exists(sub_dir_path)
bottleneck_path = get_bottleneck_path(image_lists, label_name, index,
bottleneck_dir, category, architecture)
if not os.path.exists(bottleneck_path):
create_bottleneck_file(bottleneck_path, image_lists, label_name, index,
image_dir, category, sess, jpeg_data_tensor,
decoded_image_tensor, resized_input_tensor,
bottleneck_tensor)
with open(bottleneck_path, 'r') as bottleneck_file:
bottleneck_string = bottleneck_file.read()
did_hit_error = False
try:
bottleneck_values = [float(x) for x in bottleneck_string.split(',')]
except ValueError:
tf.logging.warning('Invalid float found, recreating bottleneck')
did_hit_error = True
if did_hit_error:
create_bottleneck_file(bottleneck_path, image_lists, label_name, index,
image_dir, category, sess, jpeg_data_tensor,
decoded_image_tensor, resized_input_tensor,
bottleneck_tensor)
with open(bottleneck_path, 'r') as bottleneck_file:
bottleneck_string = bottleneck_file.read()
# Allow exceptions to propagate here, since they shouldn't happen after a
# fresh creation
bottleneck_values = [float(x) for x in bottleneck_string.split(',')]
return bottleneck_values