diff --git a/bob/bio/face/annotator/__init__.py b/bob/bio/face/annotator/__init__.py
index 8e778f616503380d8d88c266d036e08d1355a96b..e06a34aec272550003d15ea93b8f3c15ff393213 100644
--- a/bob/bio/face/annotator/__init__.py
+++ b/bob/bio/face/annotator/__init__.py
@@ -1,6 +1,5 @@
import bob.ip.facedetect
-
def bounding_box_to_annotations(bbx):
"""Converts :any:`bob.ip.facedetect.BoundingBox` to dictionary annotations.
diff --git a/bob/bio/face/annotator/bobiptinyface.py b/bob/bio/face/annotator/bobiptinyface.py
index 595f784986dd9aa2ad7444980c3aa863429ecfc5..d2790c826d61e4510cfa1e2a61d51166f9d1e270 100644
--- a/bob/bio/face/annotator/bobiptinyface.py
+++ b/bob/bio/face/annotator/bobiptinyface.py
@@ -2,14 +2,14 @@ import bob.ip.facedetect.tinyface
from . import Base
import cv2 as cv
+
class BobIpTinyface(Base):
"""Annotator using tinyface in bob.ip.facedetect"""
-
+
def __init__(self, **kwargs):
super(BobIpTinyface, self).__init__(**kwargs)
self.tinyface = bob.ip.facedetect.tinyface.TinyFacesDetector(prob_thresh=0.5)
-
def annotate(self, image, **kwargs):
"""Annotates an image using tinyface
@@ -25,15 +25,11 @@ class BobIpTinyface(Base):
dict
Annotations with (topleft, bottomright) keys (or None).
"""
-
- annotations = self.tinyface.detect(image)
+ annotations = self.tinyface.detect(image)
if annotations is not None:
r = annotations[0]
- return {'topleft':(r[0],r[1]), 'bottomright':(r[2],r[3])}
+ return {"topleft": (r[0], r[1]), "bottomright": (r[2], r[3])}
else:
return None
-
-
-
diff --git a/bob/bio/face/config/baseline/mxnet_pipe.py b/bob/bio/face/config/baseline/mxnet_pipe.py
index b458dc70f8bd61c4d75cdee26e2227cc5737cc63..eeb062004bc0e55b3db402dfa8e39be42d9ed3cf 100644
--- a/bob/bio/face/config/baseline/mxnet_pipe.py
+++ b/bob/bio/face/config/baseline/mxnet_pipe.py
@@ -23,25 +23,36 @@ else:
fixed_positions = None
+cropped_positions = {"leye": (49, 72), "reye": (49, 38)}
-cropped_positions={'leye':(49,72), 'reye':(49,38)}
-
-preprocessor_transformer = FaceCrop(cropped_image_size=(112,112), cropped_positions={'leye':(49,72), 'reye':(49,38)}, color_channel='rgb',fixed_positions=fixed_positions)
-
-transform_extra_arguments = (None if (cropped_positions is None or fixed_positions is not None) else (("annotations", "annotations"),))
-
-
+preprocessor_transformer = FaceCrop(
+ cropped_image_size=(112, 112),
+ cropped_positions={"leye": (49, 72), "reye": (49, 38)},
+ color_channel="rgb",
+ fixed_positions=fixed_positions,
+)
+transform_extra_arguments = (
+ None
+ if (cropped_positions is None or fixed_positions is not None)
+ else (("annotations", "annotations"),)
+)
extractor_transformer = mxnet_model()
-algorithm = Distance(distance_function = scipy.spatial.distance.cosine,is_distance_function = True)
+algorithm = Distance(
+ distance_function=scipy.spatial.distance.cosine, is_distance_function=True
+)
# Chain the Transformers together
transformer = make_pipeline(
- wrap(["sample"], preprocessor_transformer,transform_extra_arguments=transform_extra_arguments),
+ wrap(
+ ["sample"],
+ preprocessor_transformer,
+ transform_extra_arguments=transform_extra_arguments,
+ ),
wrap(["sample"], extractor_transformer)
# Add more transformers here if needed
)
@@ -50,5 +61,3 @@ transformer = make_pipeline(
# Assemble the Vanilla Biometric pipeline and execute
pipeline = VanillaBiometricsPipeline(transformer, algorithm)
transformer = pipeline.transformer
-
-
diff --git a/bob/bio/face/config/baseline/opencv_pipe.py b/bob/bio/face/config/baseline/opencv_pipe.py
index c7f8cd8cf005f81900f56ee354086065ede667e4..aac2d3f1c45559e35545fb66a5c02ca97aa76790 100644
--- a/bob/bio/face/config/baseline/opencv_pipe.py
+++ b/bob/bio/face/config/baseline/opencv_pipe.py
@@ -26,27 +26,41 @@ else:
fixed_positions = None
+cropped_positions = {"leye": (98, 144), "reye": (98, 76)}
+# Preprocessor
+preprocessor_transformer = FaceCrop(
+ cropped_image_size=(224, 224),
+ cropped_positions={"leye": (98, 144), "reye": (98, 76)},
+ color_channel="rgb",
+ fixed_positions=fixed_positions,
+)
-cropped_positions={"leye": (98, 144), "reye": (98, 76)}
-#Preprocessor
-preprocessor_transformer = FaceCrop(cropped_image_size=(224,224), cropped_positions={"leye": (98, 144), "reye": (98, 76)}, color_channel='rgb',fixed_positions=fixed_positions)
-
-transform_extra_arguments = (None if (cropped_positions is None or fixed_positions is not None) else (("annotations", "annotations"),))
+transform_extra_arguments = (
+ None
+ if (cropped_positions is None or fixed_positions is not None)
+ else (("annotations", "annotations"),)
+)
-#Extractor
+# Extractor
extractor_transformer = opencv_model()
-#Algorithm
-algorithm = Distance(distance_function = scipy.spatial.distance.cosine,is_distance_function = True)
+# Algorithm
+algorithm = Distance(
+ distance_function=scipy.spatial.distance.cosine, is_distance_function=True
+)
## Creation of the pipeline
# Chain the Transformers together
transformer = make_pipeline(
- wrap(["sample"], preprocessor_transformer,transform_extra_arguments=transform_extra_arguments),
+ wrap(
+ ["sample"],
+ preprocessor_transformer,
+ transform_extra_arguments=transform_extra_arguments,
+ ),
wrap(["sample"], extractor_transformer)
# Add more transformers here if needed
)
diff --git a/bob/bio/face/config/baseline/pytorch_pipe_v1.py b/bob/bio/face/config/baseline/pytorch_pipe_v1.py
index 9b03a70dd1934073e3541f423d649c4c492af138..ec5c4d9d619110d81c0c576088112aee10d6d282 100644
--- a/bob/bio/face/config/baseline/pytorch_pipe_v1.py
+++ b/bob/bio/face/config/baseline/pytorch_pipe_v1.py
@@ -23,23 +23,36 @@ else:
fixed_positions = None
+cropped_positions = {"leye": (49, 72), "reye": (49, 38)}
-cropped_positions={'leye':(49,72), 'reye':(49,38)}
-
-preprocessor_transformer = FaceCrop(cropped_image_size=(224,224), cropped_positions={'leye':(49,72), 'reye':(49,38)}, color_channel='rgb',fixed_positions=fixed_positions)
-
-transform_extra_arguments = (None if (cropped_positions is None or fixed_positions is not None) else (("annotations", "annotations"),))
+preprocessor_transformer = FaceCrop(
+ cropped_image_size=(224, 224),
+ cropped_positions={"leye": (49, 72), "reye": (49, 38)},
+ color_channel="rgb",
+ fixed_positions=fixed_positions,
+)
+transform_extra_arguments = (
+ None
+ if (cropped_positions is None or fixed_positions is not None)
+ else (("annotations", "annotations"),)
+)
extractor_transformer = pytorch_loaded_model()
-algorithm = Distance(distance_function = scipy.spatial.distance.cosine,is_distance_function = True)
+algorithm = Distance(
+ distance_function=scipy.spatial.distance.cosine, is_distance_function=True
+)
# Chain the Transformers together
transformer = make_pipeline(
- wrap(["sample"], preprocessor_transformer,transform_extra_arguments=transform_extra_arguments),
+ wrap(
+ ["sample"],
+ preprocessor_transformer,
+ transform_extra_arguments=transform_extra_arguments,
+ ),
wrap(["sample"], extractor_transformer)
# Add more transformers here if needed
)
@@ -48,60 +61,3 @@ transformer = make_pipeline(
# Assemble the Vanilla Biometric pipeline and execute
pipeline = VanillaBiometricsPipeline(transformer, algorithm)
transformer = pipeline.transformer
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
diff --git a/bob/bio/face/config/baseline/pytorch_pipe_v2.py b/bob/bio/face/config/baseline/pytorch_pipe_v2.py
index 3a01f46784eac8f0b890efde0a291b505e42f092..8cb2af0f71f2453e6b5631fb95c226edd5292c8b 100644
--- a/bob/bio/face/config/baseline/pytorch_pipe_v2.py
+++ b/bob/bio/face/config/baseline/pytorch_pipe_v2.py
@@ -54,6 +54,7 @@ transformer = make_pipeline(
# Assemble the Vanilla Biometric pipeline and execute
pipeline = VanillaBiometricsPipeline(transformer, algorithm)
transformer = pipeline.transformer
+<<<<<<< HEAD
@@ -111,3 +112,5 @@ transformer = pipeline.transformer
+=======
+>>>>>>> â€newâ€
diff --git a/bob/bio/face/config/baseline/tf_pipe.py b/bob/bio/face/config/baseline/tf_pipe.py
index 2e0a8ae2af52fcc85ac9e1a49e8bc3cf0cd2772a..22c24d95abcf88bf1acb9c9fe9f587fbd7abeccd 100644
--- a/bob/bio/face/config/baseline/tf_pipe.py
+++ b/bob/bio/face/config/baseline/tf_pipe.py
@@ -24,23 +24,38 @@ else:
# Preprocessor
-cropped_positions={'leye':(49,72), 'reye':(49,38)}
+cropped_positions = {"leye": (49, 72), "reye": (49, 38)}
-preprocessor_transformer = FaceCrop(cropped_image_size=(160,160), cropped_positions={'leye':(49,72), 'reye':(49,38)}, color_channel='rgb',fixed_positions=fixed_positions)
+preprocessor_transformer = FaceCrop(
+ cropped_image_size=(160, 160),
+ cropped_positions={"leye": (49, 72), "reye": (49, 38)},
+ color_channel="rgb",
+ fixed_positions=fixed_positions,
+)
-transform_extra_arguments = (None if (cropped_positions is None or fixed_positions is not None) else (("annotations", "annotations"),))
+transform_extra_arguments = (
+ None
+ if (cropped_positions is None or fixed_positions is not None)
+ else (("annotations", "annotations"),)
+)
# Extractor
extractor_transformer = tf_model()
# Algorithm
-algorithm = Distance(distance_function = scipy.spatial.distance.cosine,is_distance_function = True)
+algorithm = Distance(
+ distance_function=scipy.spatial.distance.cosine, is_distance_function=True
+)
# Chain the Transformers together
transformer = make_pipeline(
- wrap(["sample"], preprocessor_transformer,transform_extra_arguments=transform_extra_arguments),
+ wrap(
+ ["sample"],
+ preprocessor_transformer,
+ transform_extra_arguments=transform_extra_arguments,
+ ),
wrap(["sample"], extractor_transformer)
# Add more transformers here if needed
)
@@ -49,60 +64,3 @@ transformer = make_pipeline(
# Assemble the Vanilla Biometric pipeline and execute
pipeline = VanillaBiometricsPipeline(transformer, algorithm)
transformer = pipeline.transformer
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
diff --git a/bob/bio/face/extractor/__init__.py b/bob/bio/face/extractor/__init__.py
index a5484ea167a1afedc102965674fe8ed2ae9f5cdb..32b97163775852dbca316f538672be6bccf2095d 100644
--- a/bob/bio/face/extractor/__init__.py
+++ b/bob/bio/face/extractor/__init__.py
@@ -9,7 +9,7 @@ from .opencv_caffe import opencv_model
# gets sphinx autodoc done right - don't remove it
def __appropriate__(*args):
- """Says object was actually declared here, and not in the import module.
+ """Says object was actually declared here, and not in the import module.
Fixing sphinx warnings of not being able to find classes, when path is shortened.
Parameters:
@@ -19,7 +19,9 @@ def __appropriate__(*args):
<https://github.com/sphinx-doc/sphinx/issues/3048>`
"""
- for obj in args: obj.__module__ = __name__
+ for obj in args:
+ obj.__module__ = __name__
+
__appropriate__(
DCTBlocks,
@@ -30,5 +32,5 @@ __appropriate__(
pytorch_library_model,
tf_model,
opencv_model,
- )
-__all__ = [_ for _ in dir() if not _.startswith('_')]
+)
+__all__ = [_ for _ in dir() if not _.startswith("_")]
diff --git a/bob/bio/face/extractor/mxnet_resnet.py b/bob/bio/face/extractor/mxnet_resnet.py
index aab050bfadd851e015e8b19e736a52aa854807e9..73ab9f22a070ac198e2f8d7dfbcb6c23bb1f4221 100644
--- a/bob/bio/face/extractor/mxnet_resnet.py
+++ b/bob/bio/face/extractor/mxnet_resnet.py
@@ -12,9 +12,11 @@ import mxnet as mx
from mxnet import gluon
import warnings
from bob.extension import rc
+
mxnet_resnet_directory = rc["bob.extractor_model.mxnet"]
mxnet_weight_directory = rc["bob.extractor_weights.mxnet"]
+
class mxnet_model(TransformerMixin, BaseEstimator):
"""Extracts features using deep face recognition models under MxNet Interfaces.
@@ -57,8 +59,10 @@ class mxnet_model(TransformerMixin, BaseEstimator):
with warnings.catch_warnings():
warnings.simplefilter("ignore")
- deserialized_net = gluon.nn.SymbolBlock.imports(mxnet_resnet_directory, ['data'], mxnet_weight_directory, ctx=ctx)
-
+ deserialized_net = gluon.nn.SymbolBlock.imports(
+ mxnet_resnet_directory, ["data"], mxnet_weight_directory, ctx=ctx
+ )
+
self.model = deserialized_net
def transform(self, X):
@@ -76,16 +80,15 @@ class mxnet_model(TransformerMixin, BaseEstimator):
feature : 2D, 3D, or 4D :py:class:`numpy.ndarray` (floats)
The list of features extracted from the image.
"""
-
+
if self.model is None:
- self.load_model()
+ self._load_model()
X = check_array(X, allow_nd=True)
X = mx.nd.array(X)
return self.model(X,).asnumpy()
-
def __getstate__(self):
# Handling unpicklable objects
diff --git a/bob/bio/face/extractor/opencv_caffe.py b/bob/bio/face/extractor/opencv_caffe.py
index 647fc724fe4e1087e488f89e24ed42de750552fa..d816e0421b514e8623972b5375df7036fe91c039 100644
--- a/bob/bio/face/extractor/opencv_caffe.py
+++ b/bob/bio/face/extractor/opencv_caffe.py
@@ -44,7 +44,6 @@ class opencv_model(TransformerMixin, BaseEstimator):
use_gpu: True or False.
"""
-
def __init__(self, use_gpu=False, **kwargs):
super().__init__(**kwargs)
self.model = None
@@ -64,7 +63,7 @@ class opencv_model(TransformerMixin, BaseEstimator):
def _load_model(self):
- net = cv2.dnn.readNetFromCaffe(opencv_model_prototxt,opencv_model_directory)
+ net = cv2.dnn.readNetFromCaffe(opencv_model_prototxt, opencv_model_directory)
self.model = net
@@ -83,16 +82,15 @@ class opencv_model(TransformerMixin, BaseEstimator):
feature : 2D or 3D :py:class:`numpy.ndarray` (floats)
The list of features extracted from the image.
"""
-
+
if self.model is None:
- self.load_model()
+ self._load_model()
img = np.array(X)
self.model.setInput(img)
-
- return self.model.forward()
+ return self.model.forward()
def __getstate__(self):
# Handling unpicklable objects
diff --git a/bob/bio/face/extractor/pytorch_model.py b/bob/bio/face/extractor/pytorch_model.py
index 52c4f172d1c74f7018429261a072d8185bd69289..96a57cb9e1f45cd2a85a643146e69b3d873e787a 100644
--- a/bob/bio/face/extractor/pytorch_model.py
+++ b/bob/bio/face/extractor/pytorch_model.py
@@ -16,6 +16,7 @@ import imp
pytorch_model_directory = rc["bob.extractor_model.pytorch"]
pytorch_weight_directory = rc["bob.extractor_weights.pytorch"]
+
class pytorch_loaded_model(TransformerMixin, BaseEstimator):
"""Extracts features using deep face recognition models under PyTorch Interface, especially for the models and weights that need to load by hand.
@@ -30,7 +31,7 @@ class pytorch_loaded_model(TransformerMixin, BaseEstimator):
**Parameters:**
use_gpu: True or False.
- """
+ """
def __init__(self, use_gpu=False, **kwargs):
super().__init__(**kwargs)
@@ -52,12 +53,12 @@ class pytorch_loaded_model(TransformerMixin, BaseEstimator):
def _load_model(self):
- MainModel = imp.load_source('MainModel', pytorch_model_directory)
+ MainModel = imp.load_source("MainModel", pytorch_model_directory)
network = torch.load(pytorch_weight_directory)
network.eval()
-
- self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-
+
+ self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
network.to(self.device)
self.model = network
@@ -77,7 +78,7 @@ class pytorch_loaded_model(TransformerMixin, BaseEstimator):
feature : 2D or 3D :py:class:`numpy.ndarray` (floats)
The list of features extracted from the image.
"""
-
+
if self.model is None:
self.load_model()
@@ -85,7 +86,6 @@ class pytorch_loaded_model(TransformerMixin, BaseEstimator):
return self.model(X).detach().numpy()
-
def __getstate__(self):
# Handling unpicklable objects
@@ -95,14 +95,8 @@ class pytorch_loaded_model(TransformerMixin, BaseEstimator):
def _more_tags(self):
return {"stateless": True, "requires_fit": False}
-
-
-
-
-
-
-
-
+
+
class pytorch_library_model(TransformerMixin, BaseEstimator):
"""Extracts features using deep face recognition with registered model frames in the PyTorch Library.
@@ -153,7 +147,6 @@ class pytorch_library_model(TransformerMixin, BaseEstimator):
return self.model(X).detach().numpy()
-
def __getstate__(self):
# Handling unpicklable objects
diff --git a/bob/bio/face/extractor/tf_model.py b/bob/bio/face/extractor/tf_model.py
index 9e83ec389dafb05b1d9031c52338e235a9086ef8..001410786ae28278fea055c212bd9d5bd6a31972 100644
--- a/bob/bio/face/extractor/tf_model.py
+++ b/bob/bio/face/extractor/tf_model.py
@@ -17,6 +17,7 @@ from tensorflow import keras
tf_model_directory = rc["bob.extractor_model.tf"]
+
class tf_model(TransformerMixin, BaseEstimator):
"""Extracts features using deep face recognition models under TensorFlow Interface.
@@ -71,7 +72,7 @@ class tf_model(TransformerMixin, BaseEstimator):
feature : 2D or 3D :py:class:`numpy.ndarray` (floats)
The list of features extracted from the image.
"""
-
+
if self.model is None:
self.load_model()
@@ -80,10 +81,8 @@ class tf_model(TransformerMixin, BaseEstimator):
X = to_channels_last(X)
predict = self.model.predict(X)
-
return predict
-
def __getstate__(self):
# Handling unpicklable objects
diff --git a/requirements.txt b/requirements.txt
index 02e30ac5109f4d32cb93c768ec7a78195f25de94..bcd1763c12212b5e0c1ea6a1bbe82674f26f7f28 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -22,4 +22,4 @@ mxnet
opencv-python
six
scikit-image
-scikit-learn # for pipelines Tranformers
+scikit-learn # for pipelines Tranformers
\ No newline at end of file