Python API for bob.ip.tensorflow_extractor¶
Classes¶
bob.ip.tensorflow_extractor.Extractor (...[, ...]) |
Feature extractor using tensorflow |
bob.ip.tensorflow_extractor.FaceNet ([...]) |
Wrapper for the free FaceNet variant: |
Detailed API¶
-
bob.ip.tensorflow_extractor.
download_file
(url, out_file)[source]¶ Downloads a file from a given url
Parameters:
-
bob.ip.tensorflow_extractor.
get_config
()[source]¶ Returns a string containing the configuration information.
-
class
bob.ip.tensorflow_extractor.
Extractor
(checkpoint_filename, input_tensor, graph, debug=False)¶ Bases:
object
Feature extractor using tensorflow
-
__call__
(data)[source]¶ Forward the data with the loaded neural network
Parameters: image (numpy.array) – Input Data Returns: The features. Return type: numpy.array
-
__init__
(checkpoint_filename, input_tensor, graph, debug=False)[source]¶ Loads the tensorflow model
Parameters: - checkpoint_filename (str) – Path of your checkpoint. If the .meta file is providede the last checkpoint will be loaded.
- model – input_tensor: tf.Tensor used as a data entrypoint. It can be a tf.placeholder, the result of tf.train.string_input_producer, etc
- graph – A tf.Tensor containing the operations to be executed
-
-
class
bob.ip.tensorflow_extractor.
FaceNet
(model_path=None, image_size=160, **kwargs)¶ Bases:
object
Wrapper for the free FaceNet variant: https://github.com/davidsandberg/facenet
To use this class as a bob.bio.base extractor:
from bob.bio.base.extractor import Extractor class FaceNetExtractor(FaceNet, Extractor): pass extractor = FaceNetExtractor()