Commit e531188e authored by Guillaume HEUSCH's avatar Guillaume HEUSCH Committed by Tiago de Freitas Pereira

Added the DR-GAN encoder as feature extractor

added the DR-GAN encoder as a bob.bio.base.extractor [DR-GAN] removed the dependency to bob.bio.base.extractor [DR-GAN] added test for DR-GAN Organized the download mechanism Added some documentation
parent 19163493
Pipeline #15931 failed with stages
in 7 minutes 52 seconds
This diff is collapsed.
......@@ -66,6 +66,7 @@ def get_config():
from .Extractor import Extractor
from .FaceNet import FaceNet
from .DrGanMSU import DrGanMSUExtractor
# gets sphinx autodoc done right - don't remove it
......@@ -87,6 +88,7 @@ def __appropriate__(*args):
__appropriate__(
Extractor,
FaceNet,
DrGanMSUExtractor,
)
# gets sphinx autodoc done right - don't remove it
......
......@@ -46,6 +46,18 @@ def test_facenet():
output = extractor(data)
assert output.size == 128, output.shape
def test_drgan():
"""
'/remote/idiap.svm/user.active/heusch/work/dev/DR-GAN_code_wmodel/DR_GAN_model/DCGAN.model-590000'
"""
from bob.ip.tensorflow_extractor import DrGanMSUExtractor
#extractor = DrGanMSUExtractor("/idiap/project/hface/models/cnn/DR_GAN_model/", image_size=[96, 96, 3])
extractor = DrGanMSUExtractor()
data = numpy.random.rand(3, 96, 96).astype("uint8")
output = extractor(data)
assert output.size == 320, output.shape
"""
def test_output_from_meta():
......
......@@ -48,3 +48,24 @@ In this example we plot some outputs of the convolutional layer `conv1`.
.. plot:: plot/convolve.py
:include-source: False
Facenet Model
-------------
:ref:`bob.bio.base <bob.bio.base>` wrapper Facenet model.
Check `here for more info <py_api.html#bob.ip.tensorflow_extractor.FaceNet>`_
DRGan from L.Tran @ MSU:
------------------------
:ref:`bob.bio.base <bob.bio.base>` wrapper to the DRGan model trained by L.Tran @ MSU.
Check `here <py_api.html#bob.ip.tensorflow_extractor.DrGanMSUExtractor>`_ for more info
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment