Merge branch 'small-fixes' into 'master'

Small fixes

See merge request !69

bob/pad/base/algorithm/OneClassGMM.py

@@ -54,6 +54,7 @@ class OneClassGMM(Algorithm):
                  frame_level_scores_flag=False,
                  covariance_type='full',
                  reg_covar=1e-06,
+                 normalize_features=False,
                  ):
 
         Algorithm.__init__(
@@ -69,6 +70,7 @@ class OneClassGMM(Algorithm):
         self.frame_level_scores_flag = frame_level_scores_flag
         self.covariance_type = covariance_type
         self.reg_covar = reg_covar
+        self.normalize_features = normalize_features
 
         self.machine = None  # this argument will be updated with pretrained OneClassGMM machine
         self.features_mean = None  # this argument will be updated with features mean
@@ -105,7 +107,12 @@ class OneClassGMM(Algorithm):
         """
 
         # real is now mean-std normalized
-        features_norm, features_mean, features_std = mean_std_normalize(real, copy=False)
+        if self.normalize_features:
+            features_norm, features_mean, features_std = mean_std_normalize(real, copy=False)
+        else:
+            features_norm = real
+            features_mean = np.zeros(real.shape[1:], dtype=real.dtype)
+            features_std = np.ones(real.shape[1:], dtype=real.dtype)
 
         if isinstance(self.n_components, (tuple, list)) or isinstance(self.covariance_type, (tuple, list)):
             # perform grid search on covariance_type and n_components
@@ -119,7 +126,8 @@ class OneClassGMM(Algorithm):
                     logger.info("Testing for n_components: %s, covariance_type: %s", nc, cv_type)
                     gmm = mixture.GaussianMixture(
                         n_components=nc, covariance_type=cv_type,
-                        reg_covar=self.reg_covar)
+                        reg_covar=self.reg_covar,
+                        verbose=logger.level)
                     try:
                         gmm.fit(features_norm)
                     except Exception:
@@ -136,7 +144,8 @@ class OneClassGMM(Algorithm):
                 n_components=self.n_components,
                 random_state=self.random_state,
                 covariance_type=self.covariance_type,
-                reg_covar=self.reg_covar)
+                reg_covar=self.reg_covar,
+                verbose=logger.level)
 
             machine.fit(features_norm)
 
@@ -211,6 +220,7 @@ class OneClassGMM(Algorithm):
         # Save the GNN machine and normalizers:
         self.save_gmm_machine_and_mean_std(projector_file, machine,
                                            features_mean, features_std)
+        logger.info("Finished training the GMM.")
 
     # ==========================================================================
     def load_gmm_machine_and_mean_std(self, projector_file):
@@ -319,16 +329,17 @@ class OneClassGMM(Algorithm):
                 feature,
                 FrameContainer):  # if FrameContainer convert to 2D numpy array
 
-            features_array = convert_frame_cont_to_array(feature)
+            features = convert_frame_cont_to_array(feature)
 
         else:
 
-            features_array = feature
+            features = feature
 
-        features_array_norm, _, _ = mean_std_normalize(
-            features_array, self.features_mean, self.features_std, copy=False)
+        features_norm, _, _ = mean_std_normalize(
+            features, self.features_mean, self.features_std, copy=False)
+        del features
 
-        scores = self.machine.score_samples(features_array_norm)
+        scores = self.machine.score_samples(features_norm)
 
         return scores
 

bob/pad/base/algorithm/OneClassGMM2.py

@@ -8,6 +8,7 @@ import logging
 import numpy as np
 from collections.abc import Iterable
 from multiprocessing import cpu_count
+from sklearn.externals import joblib
 
 logger = logging.getLogger(__name__)
 
@@ -48,6 +49,7 @@ class OneClassGMM2(Algorithm):
         update_means=True,
         update_variances=True,
         n_threads=cpu_count(),
+        preprocessor=None,  # a scikit learn preprocessor, can be PCA for example
         **kwargs
     ):
         kwargs.setdefault("performs_projection", True)
@@ -65,12 +67,17 @@ class OneClassGMM2(Algorithm):
             n_threads=n_threads,
         )
         self.number_of_gaussians = number_of_gaussians
+        self.preprocessor = preprocessor
 
     def train_projector(self, training_features, projector_file):
         del training_features[1]
         real = convert_and_prepare_features(training_features[0], dtype="float64")
         del training_features[0]
 
+        if self.preprocessor is not None:
+            real = self.preprocessor.fit_transform(real)
+            joblib.dump(self.preprocessor, projector_file + ".pkl")
+
         if isinstance(self.number_of_gaussians, Iterable):
             logger.info(
                 "Performing grid search for GMM on number_of_gaussians: %s",
@@ -101,10 +108,15 @@ class OneClassGMM2(Algorithm):
 
     def load_projector(self, projector_file):
         self.gmm_alg.load_ubm(projector_file)
+        if self.preprocessor is not None:
+            self.preprocessor = joblib.load(projector_file + ".pkl")
 
     def project(self, feature):
         feature = convert_and_prepare_features([feature], dtype="float64")[0]
 
+        if self.preprocessor is not None:
+            feature = self.preprocessor.transform(feature)
+
         return self.gmm_alg.ubm(feature)
 
     def score(self, toscore):

bob/pad/base/algorithm/Predictions.py

@@ -29,6 +29,8 @@ class VideoPredictions(Algorithm):
 
     def score(self, predictions):
         # Assuming the predictions are the output of a softmax layer
+        if len(predictions) == 0:
+            return [float("nan")]
         predictions = predictions.as_array()[:, self.axis]
 
         if self.frame_level_scoring:

bob/pad/base/database/file.py

@@ -30,3 +30,6 @@ class PadFile(bob.bio.base.database.BioFile):
         # just copy the information
         # The attack type of the sample, None if it is a genuine sample.
         self.attack_type = attack_type
+
+    def __repr__(self):
+        return f"<File({self.id}: {self.path}, {self.client_id}, {self.attack_type})>"

bob/pad/base/utils/helper_functions.py

@@ -3,6 +3,7 @@
 
 import numpy as np
 import bob.bio.video
+from bob.io.base import vstack_features
 
 import itertools
 
@@ -78,18 +79,12 @@ def convert_list_of_frame_cont_to_array(frame_containers):
         An array containing features for all frames of all individuals.
     """
 
+    def reader(x):
+        if isinstance(x, bob.bio.video.FrameContainer):
+            return x.as_array()
+        return x
 
-    if isinstance( frame_containers[0], bob.bio.video.FrameContainer):
-
-      feature_vectors = []
-      for frame_container in frame_containers:
-          video_features_array = convert_frame_cont_to_array(
-            frame_container)
-          feature_vectors.append(video_features_array)
-    else:
-      feature_vectors = frame_containers
-
-    features_array = np.vstack(feature_vectors)
+    features_array = vstack_features(reader, frame_containers)
 
     return features_array