Merge branch 'refactor-cropping' into 'master'

Refactor baseline config helpers

See merge request !119

bob/bio/face/__init__.py

@@ -4,6 +4,7 @@ from . import algorithm
 from . import script
 from . import database
 from . import annotator
+from . import utils
 
 from . import test
 

bob/bio/face/config/baseline/arcface_insightface.py

 from bob.bio.face.embeddings.mxnet_models import ArcFaceInsightFace
-from bob.bio.face.config.baseline.helpers import embedding_transformer_112x112
-from bob.bio.base.pipelines.vanilla_biometrics import (
-    Distance,
-    VanillaBiometricsPipeline,
-)
-
-
-if "database" in locals():
-    annotation_type = database.annotation_type
-    fixed_positions = database.fixed_positions
-    memory_demanding = (
-        database.memory_demanding if hasattr(database, "memory_demanding") else False
-    )
-else:
-    annotation_type = None
-    fixed_positions = None
-    memory_demanding = False
+from bob.bio.face.utils import lookup_config_from_database
+from bob.bio.face.config.baseline.templates import arcface_baseline
 
+annotation_type, fixed_positions, memory_demanding = lookup_config_from_database(
+    locals().get("database")
+)
 
 def load(annotation_type, fixed_positions=None):
-    transformer = embedding_transformer_112x112(
-        ArcFaceInsightFace(memory_demanding=memory_demanding),
-        annotation_type,
-        fixed_positions,
-        color_channel="rgb",
-    )
 
-    algorithm = Distance()
-
-    return VanillaBiometricsPipeline(transformer, algorithm)
+    return arcface_baseline(
+        embedding=ArcFaceInsightFace(memory_demanding=memory_demanding),
+        annotation_type=annotation_type,
+        fixed_positions=fixed_positions,
+    )
 
 
 pipeline = load(annotation_type, fixed_positions)

bob/bio/face/config/baseline/dummy.py

@@ -5,21 +5,17 @@ from bob.bio.base.pipelines.vanilla_biometrics import (
     VanillaBiometricsPipeline,
 )
 from bob.pipelines.transformers import SampleLinearize
+from bob.bio.face.utils import lookup_config_from_database
 
-if "database" in locals():
-    annotation_type = database.annotation_type
-    fixed_positions = database.fixed_positions
-else:
-    annotation_type = None
-    fixed_positions = None
-
+annotation_type, fixed_positions, memory_demanding = lookup_config_from_database()
 
 import bob.ip.color
 from sklearn.base import TransformerMixin, BaseEstimator
-class ToGray(TransformerMixin, BaseEstimator):
 
+
+class ToGray(TransformerMixin, BaseEstimator):
     def transform(self, X, annotations=None):
-        return [bob.ip.color.rgb_to_gray(data)[0:10,0:10] for data in X]
+        return [bob.ip.color.rgb_to_gray(data)[0:10, 0:10] for data in X]
 
     def _more_tags(self):
         return {"stateless": True, "requires_fit": False}
@@ -34,9 +30,7 @@ def load(annotation_type, fixed_positions=None):
 
     transformer = make_pipeline(
         wrap(
-            ["sample"],
-            ToGray(),
-            transform_extra_arguments=transform_extra_arguments,
+            ["sample"], ToGray(), transform_extra_arguments=transform_extra_arguments,
         ),
         SampleLinearize(),
     )

bob/bio/face/config/baseline/facenet_sanderberg.py

 from bob.bio.face.embeddings.tf2_inception_resnet import (
     FaceNetSanderberg_20170512_110547,
 )
-from bob.bio.face.config.baseline.helpers import embedding_transformer_160x160
-from bob.bio.base.pipelines.vanilla_biometrics import (
-    Distance,
-    VanillaBiometricsPipeline,
-)
-
-memory_demanding = False
-if "database" in locals():
-    annotation_type = database.annotation_type
-    fixed_positions = database.fixed_positions
-    memory_demanding = (
-        database.memory_demanding if hasattr(database, "memory_demanding") else False
-    )
+from bob.bio.face.utils import lookup_config_from_database
+from bob.bio.face.config.baseline.templates import facenet_baseline
 
-else:
-    annotation_type = None
-    fixed_positions = None
+annotation_type, fixed_positions, memory_demanding = lookup_config_from_database(
+    locals().get("database")
+)
 
 
 def load(annotation_type, fixed_positions=None):
-
-    transformer = embedding_transformer_160x160(
-        FaceNetSanderberg_20170512_110547(memory_demanding=memory_demanding),
-        annotation_type,
-        fixed_positions,
+    return facenet_baseline(
+        embedding=FaceNetSanderberg_20170512_110547(memory_demanding=memory_demanding),
+        annotation_type=annotation_type,
+        fixed_positions=fixed_positions,
     )
-    algorithm = Distance()
-
-    return VanillaBiometricsPipeline(transformer, algorithm)
 
 
 pipeline = load(annotation_type, fixed_positions)

bob/bio/face/config/baseline/gabor_graph.py

@@ -3,7 +3,11 @@ from bob.bio.base.pipelines.vanilla_biometrics import (
     VanillaBiometricsPipeline,
     BioAlgorithmLegacy,
 )
-from bob.bio.face.config.baseline.helpers import crop_80x64
+from bob.bio.face.utils import (
+    lookup_config_from_database,
+    legacy_default_cropping,
+    make_cropper,
+)
 import math
 import numpy as np
 import bob.bio.face
@@ -17,20 +21,9 @@ import logging
 logger = logging.getLogger(__name__)
 
 #### SOLVING IF THERE'S ANY DATABASE INFORMATION
-if "database" in locals():
-    annotation_type = database.annotation_type
-    fixed_positions = database.fixed_positions
-else:
-    annotation_type = None
-    fixed_positions = None
-
-
-def get_cropper(annotation_type, fixed_positions=None):
-    # Cropping
-    face_cropper, transform_extra_arguments = crop_80x64(
-        annotation_type, fixed_positions, color_channel="gray"
-    )
-    return face_cropper, transform_extra_arguments
+annotation_type, fixed_positions, memory_demanding = lookup_config_from_database(
+    locals().get("database")
+)
 
 
 def get_pipeline(face_cropper, transform_extra_arguments):
@@ -80,9 +73,22 @@ def get_pipeline(face_cropper, transform_extra_arguments):
 
 def load(annotation_type, fixed_positions=None):
     ####### SOLVING THE FACE CROPPER TO BE USED ##########
-    face_cropper, transform_extra_arguments = get_cropper(
-        annotation_type, fixed_positions
+
+    # Define cropped positions
+    CROPPED_IMAGE_HEIGHT = 80
+    CROPPED_IMAGE_WIDTH = CROPPED_IMAGE_HEIGHT * 4 // 5
+    cropped_image_size = (CROPPED_IMAGE_HEIGHT, CROPPED_IMAGE_WIDTH)
+    cropped_positions = legacy_default_cropping(cropped_image_size, annotation_type)
+
+    # Cropping
+    face_cropper, transform_extra_arguments = make_cropper(
+        cropped_image_size=cropped_image_size,
+        cropped_positions=cropped_positions,
+        fixed_positions=fixed_positions,
+        color_channel="gray",
+        annotator="mtcnn",
     )
+
     return get_pipeline(face_cropper, transform_extra_arguments)
 
 

bob/bio/face/config/baseline/inception_resnetv1_casiawebface.py

 from bob.bio.face.embeddings.tf2_inception_resnet import (
     InceptionResnetv1_Casia_CenterLoss_2018,
 )
-from bob.bio.face.config.baseline.helpers import embedding_transformer_160x160
-from bob.bio.base.pipelines.vanilla_biometrics import (
-    Distance,
-    VanillaBiometricsPipeline,
-)
-
-memory_demanding = False
-if "database" in locals():
-    annotation_type = database.annotation_type
-    fixed_positions = database.fixed_positions
-    memory_demanding = (
-        database.memory_demanding if hasattr(database, "memory_demanding") else False
-    )
+from bob.bio.face.utils import lookup_config_from_database
+from bob.bio.face.config.baseline.templates import facenet_baseline
 
-else:
-    annotation_type = None
-    fixed_positions = None
+annotation_type, fixed_positions, memory_demanding = lookup_config_from_database(
+    locals().get("database")
+)
 
 
 def load(annotation_type, fixed_positions=None):
-    transformer = embedding_transformer_160x160(
-        InceptionResnetv1_Casia_CenterLoss_2018(memory_demanding=memory_demanding),
-        annotation_type,
-        fixed_positions,
+    return facenet_baseline(
+        embedding=InceptionResnetv1_Casia_CenterLoss_2018(
+            memory_demanding=memory_demanding
+        ),
+        annotation_type=annotation_type,
+        fixed_positions=fixed_positions,
     )
 
-    algorithm = Distance()
-
-    return VanillaBiometricsPipeline(transformer, algorithm)
-
 
 pipeline = load(annotation_type, fixed_positions)
 transformer = pipeline.transformer

bob/bio/face/config/baseline/inception_resnetv1_msceleb.py

 from bob.bio.face.embeddings.tf2_inception_resnet import (
     InceptionResnetv1_MsCeleb_CenterLoss_2018,
 )
-from bob.bio.face.config.baseline.helpers import embedding_transformer_160x160
-from bob.bio.base.pipelines.vanilla_biometrics import (
-    Distance,
-    VanillaBiometricsPipeline,
-)
+from bob.bio.face.utils import lookup_config_from_database
+from bob.bio.face.config.baseline.templates import facenet_baseline
 
-memory_demanding = False
-if "database" in locals():
-    annotation_type = database.annotation_type
-    fixed_positions = database.fixed_positions
-    memory_demanding = (
-        database.memory_demanding if hasattr(database, "memory_demanding") else False
-    )
 
-else:
-    annotation_type = None
-    fixed_positions = None
+annotation_type, fixed_positions, memory_demanding = lookup_config_from_database(
+    locals().get("database")
+)
 
 
 def load(annotation_type, fixed_positions=None):
-    transformer = embedding_transformer_160x160(
-        InceptionResnetv1_MsCeleb_CenterLoss_2018(memory_demanding=memory_demanding),
-        annotation_type,
-        fixed_positions,
+    return facenet_baseline(
+        embedding=InceptionResnetv1_MsCeleb_CenterLoss_2018(
+            memory_demanding=memory_demanding
+        ),
+        annotation_type=annotation_type,
+        fixed_positions=fixed_positions,
     )
 
-    algorithm = Distance()
-
-    return VanillaBiometricsPipeline(transformer, algorithm)
-
 
 pipeline = load(annotation_type, fixed_positions)
 transformer = pipeline.transformer

bob/bio/face/config/baseline/inception_resnetv2_casiawebface.py

 from bob.bio.face.embeddings.tf2_inception_resnet import (
     InceptionResnetv2_Casia_CenterLoss_2018,
 )
-from bob.bio.face.config.baseline.helpers import embedding_transformer_160x160
-from bob.bio.base.pipelines.vanilla_biometrics import (
-    Distance,
-    VanillaBiometricsPipeline,
-)
+from bob.bio.face.utils import lookup_config_from_database
+from bob.bio.face.config.baseline.templates import facenet_baseline
 
-memory_demanding = False
-if "database" in locals():
-    annotation_type = database.annotation_type
-    fixed_positions = database.fixed_positions
-    memory_demanding = (
-        database.memory_demanding if hasattr(database, "memory_demanding") else False
-    )
 
-else:
-    annotation_type = None
-    fixed_positions = None
+annotation_type, fixed_positions, memory_demanding = lookup_config_from_database(
+    locals().get("database")
+)
 
 
 def load(annotation_type, fixed_positions=None):
-    transformer = embedding_transformer_160x160(
-        InceptionResnetv2_Casia_CenterLoss_2018(memory_demanding=memory_demanding),
-        annotation_type,
-        fixed_positions,
+    return facenet_baseline(
+        embedding=InceptionResnetv2_Casia_CenterLoss_2018(
+            memory_demanding=memory_demanding
+        ),
+        annotation_type=annotation_type,
+        fixed_positions=fixed_positions,
     )
 
-    algorithm = Distance()
-
-    return VanillaBiometricsPipeline(transformer, algorithm)
-
 
 pipeline = load(annotation_type, fixed_positions)
 transformer = pipeline.transformer

bob/bio/face/config/baseline/inception_resnetv2_msceleb.py

 from bob.bio.face.embeddings.tf2_inception_resnet import (
     InceptionResnetv2_MsCeleb_CenterLoss_2018,
 )
-from bob.bio.face.config.baseline.helpers import embedding_transformer_160x160
-from bob.bio.base.pipelines.vanilla_biometrics import (
-    Distance,
-    VanillaBiometricsPipeline,
-)
-
-memory_demanding = False
-if "database" in locals():
-    annotation_type = database.annotation_type
-    fixed_positions = database.fixed_positions
+from bob.bio.face.utils import lookup_config_from_database
+from bob.bio.face.config.baseline.templates import facenet_baseline
 
-    memory_demanding = (
-        database.memory_demanding if hasattr(database, "memory_demanding") else False
-    )
-else:
-    annotation_type = None
-    fixed_positions = None
+annotation_type, fixed_positions, memory_demanding = lookup_config_from_database(
+    locals().get("database")
+)
 
 
 def load(annotation_type, fixed_positions=None):
-    transformer = embedding_transformer_160x160(
-        InceptionResnetv2_MsCeleb_CenterLoss_2018(memory_demanding=memory_demanding),
-        annotation_type,
-        fixed_positions,
+    return facenet_baseline(
+        embedding=InceptionResnetv2_MsCeleb_CenterLoss_2018(
+            memory_demanding=memory_demanding
+        ),
+        annotation_type=annotation_type,
+        fixed_positions=fixed_positions,
     )
 
-    algorithm = Distance()
-
-    return VanillaBiometricsPipeline(transformer, algorithm)
-
 
 pipeline = load(annotation_type, fixed_positions)
 transformer = pipeline.transformer

bob/bio/face/config/baseline/lda.py

@@ -3,7 +3,11 @@ from bob.bio.base.pipelines.vanilla_biometrics import (
     VanillaBiometricsPipeline,
     BioAlgorithmLegacy,
 )
-from bob.bio.face.config.baseline.helpers import crop_80x64
+from bob.bio.face.utils import (
+    lookup_config_from_database,
+    legacy_default_cropping,
+    make_cropper,
+)
 import numpy as np
 import bob.bio.face
 from sklearn.pipeline import make_pipeline
@@ -18,20 +22,27 @@ import logging
 logger = logging.getLogger(__name__)
 
 #### SOLVING IF THERE'S ANY DATABASE INFORMATION
-if "database" in locals():
-    annotation_type = database.annotation_type
-    fixed_positions = database.fixed_positions
-else:
-    annotation_type = None
-    fixed_positions = None
+annotation_type, fixed_positions, memory_demanding = lookup_config_from_database(
+    locals().get("database")
+)
 
 
 ####### SOLVING THE FACE CROPPER TO BE USED ##########
 def load(annotation_type, fixed_positions=None):
 
+    # Define cropped positions
+    CROPPED_IMAGE_HEIGHT = 80
+    CROPPED_IMAGE_WIDTH = CROPPED_IMAGE_HEIGHT * 4 // 5
+    cropped_image_size = (CROPPED_IMAGE_HEIGHT, CROPPED_IMAGE_WIDTH)
+    cropped_positions = legacy_default_cropping(cropped_image_size, annotation_type)
+
     # Cropping
-    face_cropper, transform_extra_arguments = crop_80x64(
-        annotation_type, fixed_positions, color_channel="gray"
+    face_cropper, transform_extra_arguments = make_cropper(
+        cropped_image_size=cropped_image_size,
+        cropped_positions=cropped_positions,
+        fixed_positions=fixed_positions,
+        color_channel="gray",
+        annotator="mtcnn",
     )
 
     preprocessor = bob.bio.face.preprocessor.TanTriggs(

bob/bio/face/config/baseline/lgbphs.py

@@ -3,7 +3,11 @@ from bob.bio.base.pipelines.vanilla_biometrics import (
     VanillaBiometricsPipeline,
     BioAlgorithmLegacy,
 )
-from bob.bio.face.config.baseline.helpers import crop_80x64
+from bob.bio.face.utils import (
+    lookup_config_from_database,
+    legacy_default_cropping,
+    make_cropper,
+)
 import math
 import numpy as np
 import bob.bio.face
@@ -13,20 +17,9 @@ import bob.math
 
 
 #### SOLVING IF THERE'S ANY DATABASE INFORMATION
-if "database" in locals():
-    annotation_type = database.annotation_type
-    fixed_positions = database.fixed_positions
-else:
-    annotation_type = None
-    fixed_positions = None
-
-
-def get_cropper(annotation_type, fixed_positions=None):
-    # Cropping
-    face_cropper, transform_extra_arguments = crop_80x64(
-        annotation_type, fixed_positions, color_channel="gray"
-    )
-    return face_cropper, transform_extra_arguments
+annotation_type, fixed_positions, memory_demanding = lookup_config_from_database(
+    locals().get("database")
+)
 
 
 def get_pipeline(face_cropper, transform_extra_arguments):
@@ -70,10 +63,22 @@ def get_pipeline(face_cropper, transform_extra_arguments):
 
 
 def load(annotation_type, fixed_positions=None):
+    # Define cropped positions
+    CROPPED_IMAGE_HEIGHT = 80
+    CROPPED_IMAGE_WIDTH = CROPPED_IMAGE_HEIGHT * 4 // 5
+    cropped_image_size = (CROPPED_IMAGE_HEIGHT, CROPPED_IMAGE_WIDTH)
+    cropped_positions = legacy_default_cropping(cropped_image_size, annotation_type)
+
     ####### SOLVING THE FACE CROPPER TO BE USED ##########
-    face_cropper, transform_extra_arguments = get_cropper(
-        annotation_type, fixed_positions
+    # Cropping
+    face_cropper, transform_extra_arguments = make_cropper(
+        cropped_image_size=cropped_image_size,
+        cropped_positions=cropped_positions,
+        fixed_positions=fixed_positions,
+        color_channel="gray",
+        annotator="mtcnn",
     )
+
     return get_pipeline(face_cropper, transform_extra_arguments)
 
 

bob/bio/face/config/baseline/mobilenetv2_msceleb_arcface_2021.py

 from bob.bio.face.embeddings.mobilenet_v2 import MobileNetv2_MsCeleb_ArcFace_2021
-from bob.bio.face.config.baseline.helpers import embedding_transformer_112x112
-from bob.bio.base.pipelines.vanilla_biometrics import (
-    Distance,
-    VanillaBiometricsPipeline,
-)
+from bob.bio.face.utils import lookup_config_from_database
+from bob.bio.face.config.baseline.templates import arcface_baseline
 
-memory_demanding = False
-if "database" in locals():
-    annotation_type = database.annotation_type
-    fixed_positions = database.fixed_positions
 
-    memory_demanding = (
-        database.memory_demanding if hasattr(database, "memory_demanding") else False
-    )
-else:
-    annotation_type = None
-    fixed_positions = None
+annotation_type, fixed_positions, memory_demanding = lookup_config_from_database(
+    locals().get("database")
+)
 
 
 def load(annotation_type, fixed_positions=None):
-    transformer = embedding_transformer_112x112(
-        MobileNetv2_MsCeleb_ArcFace_2021(memory_demanding=memory_demanding),
-        annotation_type,
-        fixed_positions,
-    )
-
-    algorithm = Distance()
 
-    return VanillaBiometricsPipeline(transformer, algorithm)
+    return arcface_baseline(
+        embedding=MobileNetv2_MsCeleb_ArcFace_2021(memory_demanding=memory_demanding),
+        annotation_type=annotation_type,
+        fixed_positions=fixed_positions,
+    )
 
 
 pipeline = load(annotation_type, fixed_positions)

bob/bio/face/config/baseline/resnet50_msceleb_arcface_2021.py

 from bob.bio.face.embeddings.resnet50 import Resnet50_MsCeleb_ArcFace_2021
-from bob.bio.face.config.baseline.helpers import embedding_transformer_112x112
-from bob.bio.base.pipelines.vanilla_biometrics import (
-    Distance,
-    VanillaBiometricsPipeline,
-)
+from bob.bio.face.utils import lookup_config_from_database
+from bob.bio.face.config.baseline.templates import arcface_baseline
 
-memory_demanding = False
-if "database" in locals():
-    annotation_type = database.annotation_type
-    fixed_positions = database.fixed_positions
 
-    memory_demanding = (
-        database.memory_demanding if hasattr(database, "memory_demanding") else False
-    )
-else:
-    annotation_type = None
-    fixed_positions = None
+annotation_type, fixed_positions, memory_demanding = lookup_config_from_database(
+    locals().get("database")
+)
 
 
 def load(annotation_type, fixed_positions=None):
-    transformer = embedding_transformer_112x112(
-        Resnet50_MsCeleb_ArcFace_2021(memory_demanding=memory_demanding),
-        annotation_type,
-        fixed_positions,
+    return arcface_baseline(
+        embedding=Resnet50_MsCeleb_ArcFace_2021(memory_demanding=memory_demanding),
+        annotation_type=annotation_type,
+        fixed_positions=fixed_positions,
     )
 
-    algorithm = Distance()
-
-    return VanillaBiometricsPipeline(transformer, algorithm)
-
 
 pipeline = load(annotation_type, fixed_positions)
 transformer = pipeline.transformer

bob/bio/face/config/baseline/resnet50_vgg2_arcface_2021.py

 from bob.bio.face.embeddings.resnet50 import Resnet50_VGG2_ArcFace_2021
-from bob.bio.face.config.baseline.helpers import embedding_transformer_112x112
-from bob.bio.base.pipelines.vanilla_biometrics import (
-    Distance,