Included two new baselines

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,
+)
+
+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
+
+
+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)
+
+
+pipeline = load(annotation_type, fixed_positions)
+transformer = pipeline.transformer

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,
+)
+
+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
+
+
+def load(annotation_type, fixed_positions=None):
+    transformer = embedding_transformer_112x112(
+        Resnet50_MsCeleb_ArcFace_2021(memory_demanding=memory_demanding),
+        annotation_type,
+        fixed_positions,
+    )
+
+    algorithm = Distance()
+
+    return VanillaBiometricsPipeline(transformer, algorithm)
+
+
+pipeline = load(annotation_type, fixed_positions)
+transformer = pipeline.transformer

bob/bio/face/embeddings/mobilenet_v2.py

+from bob.bio.face.embeddings import download_model
+
+
+from .tf2_inception_resnet import TransformTensorflow
+import pkg_resources
+import os
+from bob.extension import rc
+import tensorflow as tf
+
+
+class MobileNetv2_MsCeleb_ArcFace_2021(TransformTensorflow):
+    """
+    MobileNet Backbone trained with the MSCeleb 1M database.
+
+    The bottleneck layer (a.k.a embedding) has 512d.
+
+    The configuration file used to trained is:
+
+    ```yaml
+    batch-size: 128
+    face-size: 112
+    face-output_size: 112
+    n-classes: 85742
+
+
+    ## Backbone
+    backbone: 'mobilenet-v2'
+    head: 'arcface'
+    s: 10
+    bottleneck: 512
+    m: 0.5
+
+    # Training parameters
+    solver: "sgd"
+    lr: 0.01
+    dropout-rate: 0.5
+    epochs: 500
+
+
+    train-tf-record-path: "<PATH>"
+    validation-tf-record-path: "<PATH>"
+
+    ```
+
+
+    """
+
+    def __init__(self, memory_demanding=False):
+        internal_path = pkg_resources.resource_filename(
+            __name__, os.path.join("data", "mobilenet-v2-msceleb-arcface-2021"),
+        )
+
+        checkpoint_path = (
+            internal_path
+            if rc["bob.bio.face.models.mobilenet-v2-msceleb-arcface-2021"] is None
+            else rc["bob.bio.face.models.mobilenet-v2-msceleb-arcface-2021"]
+        )
+
+        urls = [
+            "https://www.idiap.ch/software/bob/data/bob/bob.bio.face/master/tf2/mobilenet-v2-msceleb-arcface-2021.tar.gz",
+            "http://www.idiap.ch/software/bob/data/bob/bob.bio.face/master/tf2/mobilenet-v2-msceleb-arcface-2021.tar.gz",
+        ]
+
+        download_model(checkpoint_path, urls, "mobilenet-v2-msceleb-arcface-2021.tar.gz")
+
+        super(MobileNetv2_MsCeleb_ArcFace_2021, self).__init__(
+            checkpoint_path,
+            preprocessor=lambda X: X / 255.0,
+            memory_demanding=memory_demanding,
+        )
+
+    def inference(self, X):
+        if self.preprocessor is not None:
+            X = self.preprocessor(tf.cast(X, "float32"))
+
+        prelogits = self.model.predict_on_batch(X)[0]
+        embeddings = tf.math.l2_normalize(prelogits, axis=-1)
+        return embeddings
+

bob/bio/face/embeddings/resnet50.py

+from bob.bio.face.embeddings import download_model
+
+
+from .tf2_inception_resnet import TransformTensorflow
+import pkg_resources
+import os
+from bob.extension import rc
+import tensorflow as tf
+
+
+class Resnet50_MsCeleb_ArcFace_2021(TransformTensorflow):
+    """
+    Resnet50 Backbone trained with the MSCeleb 1M database.
+
+    The bottleneck layer (a.k.a embedding) has 512d.
+
+    The configuration file used to trained is:
+
+    ```yaml
+    batch-size: 128
+    face-size: 112
+    face-output_size: 112
+    n-classes: 85742
+
+
+    ## Backbone
+    backbone: 'resnet50'
+    head: 'arcface'
+    s: 10
+    bottleneck: 512
+    m: 0.5
+
+    # Training parameters
+    solver: "sgd"
+    lr: 0.01
+    dropout-rate: 0.5
+    epochs: 500
+
+
+    train-tf-record-path: "<PATH>"
+    validation-tf-record-path: "<PATH>"
+
+    ```
+
+
+    """
+
+    def __init__(self, memory_demanding=False):
+        internal_path = pkg_resources.resource_filename(
+            __name__, os.path.join("data", "resnet50_msceleb_arcface_2021"),
+        )
+
+        checkpoint_path = (
+            internal_path
+            if rc["bob.bio.face.models.resnet50_msceleb_arcface_2021"] is None
+            else rc["bob.bio.face.models.resnet50_msceleb_arcface_2021"]
+        )
+
+        urls = [
+            "https://www.idiap.ch/software/bob/data/bob/bob.bio.face/master/tf2/resnet50_msceleb_arcface_2021.tar.gz",
+            "http://www.idiap.ch/software/bob/data/bob/bob.bio.face/master/tf2/resnet50_msceleb_arcface_2021.tar.gz",
+        ]
+
+        download_model(checkpoint_path, urls, "resnet50_msceleb_arcface_2021.tar.gz")
+
+        super(Resnet50_MsCeleb_ArcFace_2021, self).__init__(
+            checkpoint_path,
+            preprocessor=lambda X: X / 255.0,
+            memory_demanding=memory_demanding,
+        )
+
+    def inference(self, X):
+        if self.preprocessor is not None:
+            X = self.preprocessor(tf.cast(X, "float32"))
+
+        prelogits = self.model.predict_on_batch(X)[0]
+        embeddings = tf.math.l2_normalize(prelogits, axis=-1)
+        return embeddings
+

bob/bio/face/embeddings/tf2_inception_resnet.py

@@ -52,14 +52,6 @@ class TransformTensorflow(TransformerMixin, BaseEstimator):
     def load_model(self):
         self.model = tf.keras.models.load_model(self.checkpoint_path)
 
-    def inference(self, X):
-        if self.preprocessor is not None:
-            X = self.preprocessor(tf.cast(X, "float32"))
-
-        prelogits = self.model.predict_on_batch(X)
-        embeddings = tf.math.l2_normalize(prelogits, axis=-1)
-        return embeddings
-
     def transform(self, X):
         def _transform(X):
             X = tf.convert_to_tensor(X)

setup.py

@@ -146,6 +146,8 @@ setup(
             "lgbphs = bob.bio.face.config.baseline.lgbphs:pipeline",
             "lda = bob.bio.face.config.baseline.lda:pipeline",
             "dummy = bob.bio.face.config.baseline.dummy:pipeline",
+            "resnet50-msceleb-arcface-2021 = bob.bio.face.config.baseline.resnet50_msceleb_arcface_2021:pipeline",
+            "mobilenetv2-msceleb-arcface-2021 = bob.bio.face.config.baseline.mobilenetv2_msceleb_arcface_2021",
         ],
         "bob.bio.config": [
             "facenet-sanderberg = bob.bio.face.config.baseline.facenet_sanderberg",
@@ -174,6 +176,8 @@ setup(
             "fargo  = bob.bio.face.config.database.fargo",
             "meds = bob.bio.face.config.database.meds",
             "morph = bob.bio.face.config.database.morph",
+            "resnet50-msceleb-arcface-2021 = bob.bio.face.config.baseline.resnet50_msceleb_arcface_2021",
+            "mobilenetv2-msceleb-arcface-2021 = bob.bio.face.config.baseline.mobilenetv2_msceleb_arcface_2021",
         ],
         "bob.bio.cli": [
             "display-face-annotations          = bob.bio.face.script.display_face_annotations:display_face_annotations",