refactoring and extending LSTM tf algo

bob/pad/voice/algorithm/gmm_algorithm.py → bob/pad/voice/algorithm/GMM.py

@@ -17,7 +17,7 @@ import logging
 logger = logging.getLogger("bob.pad.voice")
 
 
-class GmmAlgorithm(Algorithm):
+class GMM(Algorithm):
     """Trains Logistical Regression classifier and projects testing dat on it."""
 
     def __init__(self,
@@ -156,8 +156,8 @@ class GmmAlgorithm(Algorithm):
         real_features = numpy.vstack(training_features[0])
         attack_features = numpy.vstack(training_features[1])
 
-        print ("GmmAlgorithm:train_projector(), real_features shape:", real_features.shape)
-        print ("GmmAlgorithm:train_projector(), attack_features shape:", attack_features.shape)
+        print ("GMM:train_projector(), real_features shape:", real_features.shape)
+        print ("GMM:train_projector(), attack_features shape:", attack_features.shape)
         print ("Min real ", numpy.min(real_features))
         print ("Max real ", numpy.max(real_features))
         print ("Min attack ", numpy.min(attack_features))
@@ -244,4 +244,4 @@ class GmmAlgorithm(Algorithm):
         self.score(toscore)
 
 
-algorithm = GmmAlgorithm()
+algorithm = GMM()

bob/pad/voice/algorithm/histdistance_algorithm.py → bob/pad/voice/algorithm/HistDistance.py

@@ -18,7 +18,7 @@ import logging
 logger = logging.getLogger("bob.pad.voice")
 
 
-class HistDistanceAlgorithm(Algorithm):
+class HistDistance(Algorithm):
     """This class is used to test all the possible functions of the tool chain, but it does basically nothing."""
 
     def __init__(self, chi_square=False, hist_intersection=True, probab_dist=False, normalize_features=True, **kwargs):
@@ -53,10 +53,10 @@ class HistDistanceAlgorithm(Algorithm):
             raise ValueError("Training projector: features should contain two lists: real and attack!")
 
             # the format is specified in FileSelector.py:training_list() of bob.spoof.base
-        #    print ("HistDistanceAlgorithm:train_projector(), training_features", type(training_features[0][0]))
+        #    print ("HistDistance:train_projector(), training_features", type(training_features[0][0]))
 
         if isinstance(training_features[0][0][0], numpy.ndarray):
-            print ("HistDistanceAlgorithm:train_projector(), features are set of arrays of length: ",
+            print ("HistDistance:train_projector(), features are set of arrays of length: ",
                    len(training_features[0][0][0]))
             real_features = numpy.array([row for feat in training_features[0] for row in feat], dtype=numpy.float64)
             attack_features = numpy.array([row for feat in training_features[1] for row in feat], dtype=numpy.float64)
@@ -64,10 +64,10 @@ class HistDistanceAlgorithm(Algorithm):
             real_features = numpy.array(training_features[0], dtype=numpy.float64)
             attack_features = numpy.array(training_features[1], dtype=numpy.float64)
 
-        # #    print ("HistDistanceAlgorithm:train_projector(), real_features", real_features)
-        # #    print ("HistDistanceAlgorithm:train_projector(), attack_features", attack_features)
-        # print ("HistDistanceAlgorithm:train_projector(), real_features shape:", real_features.shape)
-        # print ("HistDistanceAlgorithm:train_projector(), attack_features shape:", attack_features.shape)
+        # #    print ("HistDistance:train_projector(), real_features", real_features)
+        # #    print ("HistDistance:train_projector(), attack_features", attack_features)
+        # print ("HistDistance:train_projector(), real_features shape:", real_features.shape)
+        # print ("HistDistance:train_projector(), attack_features shape:", attack_features.shape)
         # #    real_features[real_features<-1024] = -1024
         # #    attack_features[attack_features<-1024] = -1024
         # print ("Min real ", numpy.min(real_features))
@@ -135,9 +135,9 @@ class HistDistanceAlgorithm(Algorithm):
                 dist_real = bob.math.histogram_intersection(self.real_mean, feature)
                 dist_attack = bob.math.histogram_intersection(self.attack_mean, feature)
             else:
-                raise ValueError("HistDistanceAlgorithm: please specify the metric for histogram distance")
+                raise ValueError("HistDistance: please specify the metric for histogram distance")
 
-            #      print ("HistDistanceAlgorithm:project(), projection: ", projection)
+            #      print ("HistDistance:project(), projection: ", projection)
             return numpy.array([dist_real, dist_attack], dtype=numpy.float64)
             # return self.machine(feature)
         return numpy.zeros(2, dtype=numpy.float64)
@@ -158,7 +158,7 @@ class HistDistanceAlgorithm(Algorithm):
           The ``feature`` projected into Fisher space.
         """
 
-        print ("HistDistanceAlgorithm:project(), feature shape: ", feature.shape)
+        print ("HistDistance:project(), feature shape: ", feature.shape)
 
         if len(feature) > 0:
             if isinstance(feature[0], numpy.ndarray) or isinstance(feature[0], list):
@@ -170,7 +170,7 @@ class HistDistanceAlgorithm(Algorithm):
 
     def score(self, toscore):
         """Returns the evarage value of the probe"""
-        print("HistDistanceAlgorithm:score() the score: ", toscore)
+        print("HistDistance:score() the score: ", toscore)
 
         # projection is already the score in this case
         if self.probab_dist:
@@ -190,12 +190,12 @@ class HistDistanceAlgorithm(Algorithm):
             return [dist_real - dist_attack]
 
         else:
-            raise ValueError("HistDistanceAlgorithm:scoring() please specify the metric for histogram distance")
+            raise ValueError("HistDistance:scoring() please specify the metric for histogram distance")
 
     def score_for_multiple_projections(self, toscore):
-        print("HistDistanceAlgorithm:score_for_multiple_projections() the score: ", len(toscore))
+        print("HistDistance:score_for_multiple_projections() the score: ", len(toscore))
 
         return numpy.array([self.score(score) for score in toscore], dtype=numpy.float64)
 
 
-algorithm = HistDistanceAlgorithm()
+algorithm = HistDistance()

bob/pad/voice/algorithm/tensorflow_algorithm.py → bob/pad/voice/algorithm/LSTMEval.py

@@ -14,10 +14,12 @@ import logging
 logger = logging.getLogger("bob.pad.voice")
 
 
-class TensorflowAlgo(Algorithm):
+class LSTMEval(Algorithm):
     """This class is used to test all the possible functions of the tool chain, but it does basically nothing."""
 
     def __init__(self,
+                 input_shape=[200, 81],  # [temporal_length, feature_size]
+                 lstm_network_size=60,  # the output size of LSTM cell
                  **kwargs):
         """Generates a test value that is read and written"""
 
@@ -26,8 +28,13 @@ class TensorflowAlgo(Algorithm):
             self,
             performs_projection=True,
             requires_projector_training=False,
+            **kwargs
         )
 
+        self.input_shape = input_shape
+        self.num_time_steps = input_shape[0]
+        self.lstm_network_size = lstm_network_size
+
         self.data_reader = None
         self.session = None
         self.dnn_model = None
@@ -70,9 +77,9 @@ class TensorflowAlgo(Algorithm):
         import tensorflow as tf
         if self.session is None:
             self.session = tf.Session()
-        data_pl = tf.placeholder(tf.float32, shape=(None, 60, 102))
+        data_pl = tf.placeholder(tf.float32, shape=(None, ) + tuple(self.input_shape))
         graph = self.simple_lstm_network(data_pl, batch_size=1,
-                                         lstm_cell_size=60, num_time_steps=60,
+                                         lstm_cell_size=self.lstm_network_size, num_time_steps=self.num_time_steps,
                                          num_classes=2, reuse=False)
 
         self.session.run(tf.global_variables_initializer())
@@ -91,9 +98,10 @@ class TensorflowAlgo(Algorithm):
         logger.info(" .... Projecting %d features vector" % feature.shape[0])
         from bob.learn.tensorflow.datashuffler import DiskAudio
         if not self.data_reader:
-            self.data_reader = DiskAudio([0], [0], [1, 60, 102])
+            self.data_reader = DiskAudio([0], [0], [1] + self.input_shape)
         # frames, labels = self.data_reader.extract_frames_from_wav(feature, 0)
-        frames, labels = self.data_reader.split_features_in_windows(feature, 0, 60)
+        frames, labels = self.data_reader.split_features_in_windows(features=feature, label=1,
+                                                                    win_size=self.num_time_steps)
 #        frames = numpy.asarray(frames)
 #        logger.info(" .... And frames of shape {0} are extracted to pass into DNN model".format(frames.shape))
         projections = numpy.zeros((len(frames), 2), dtype=numpy.float32)
@@ -144,7 +152,7 @@ class TensorflowAlgo(Algorithm):
           A score value for the object ``toscore``.
         """
         scores = numpy.asarray(toscore, dtype=numpy.float32)
-        real_scores = scores[:, 0]
+        real_scores = scores[:, 1]
         logger.debug("Mean score %f", numpy.mean(real_scores))
         return [numpy.mean(real_scores)]
 
@@ -155,4 +163,4 @@ class TensorflowAlgo(Algorithm):
         return [toscore[0]]
 
 
-algorithm = TensorflowAlgo()
+algorithm = LSTMEval()

bob/pad/voice/algorithm/logregr_algorithm.py → bob/pad/voice/algorithm/LogRegr.py

@@ -16,7 +16,7 @@ import logging
 logger = logging.getLogger("bob.pad.voice")
 
 
-class LogRegrAlgorithm(Algorithm):
+class LogRegr(Algorithm):
     """Trains Logistical Regression classifier and projects testing dat on it."""
 
     def __init__(self, use_PCA_training=False, normalize_features=False, **kwargs):
@@ -69,8 +69,8 @@ class LogRegrAlgorithm(Algorithm):
                 [feat if self._check_feature(feat) else numpy.nan for feat in training_features[1]],
                 dtype=numpy.float64)
 
-        # print ("LogRegrAlgorithm:train_projector(), real_features shape:", real_features.shape)
-        # print ("LogRegrAlgorithm:train_projector(), attack_features shape:", attack_features.shape)
+        # print ("LogRegr:train_projector(), real_features shape:", real_features.shape)
+        # print ("LogRegr:train_projector(), attack_features shape:", attack_features.shape)
         # print ("Min real ", numpy.min(real_features))
         # print ("Max real ", numpy.max(real_features))
         # print ("Min attack ", numpy.min(attack_features))
@@ -130,8 +130,8 @@ class LogRegrAlgorithm(Algorithm):
                 self.machine.input_subtract = mean
                 self.machine.input_divide = std
 
-        # print ("LogRegrAlgorithm:train_projector(), machine shape: ", self.machine.shape)
-        # print ("LogRegrAlgorithm:train_projector(), machine weights: ", self.machine.weights)
+        # print ("LogRegr:train_projector(), machine shape: ", self.machine.shape)
+        # print ("LogRegr:train_projector(), machine weights: ", self.machine.weights)
 
         hdf5file.cd('/')
         hdf5file.create_group('LogRegProjector')
@@ -203,4 +203,4 @@ class LogRegrAlgorithm(Algorithm):
         return toscore
 
 
-algorithm = LogRegrAlgorithm()
+algorithm = LogRegr()

bob/pad/voice/algorithm/__init__.py

-from .gmm_algorithm import GmmAlgorithm
-from .logregr_algorithm import LogRegrAlgorithm
-from .tensorflow_algorithm import TensorflowAlgo
+from .GMM import GMM
+from .LogRegr import LogRegr
+from .LSTMEval import LSTMEval
 
 # gets sphinx autodoc done right - don't remove it
 def __appropriate__(*args):
@@ -17,8 +17,8 @@ def __appropriate__(*args):
   for obj in args: obj.__module__ = __name__
 
 __appropriate__(
-    GmmAlgorithm,
-    LogRegrAlgorithm,
-    TensorflowAlgo,
+    GMM,
+    LogRegr,
+    LSTMEval,
     )
 __all__ = [_ for _ in dir() if not _.startswith('_')]

bob/pad/voice/algorithm/dummy.py

+#!/usr/bin/env python
+# vim: set fileencoding=utf-8 :
+# @author: Pavel Korshunov <pavel.korshunov@idiap.ch>
+# @date: Wed 19 Oct 23:43:22 2016
+
+from bob.pad.base.algorithm import Algorithm
+
+import logging
+
+logger = logging.getLogger("bob.pad.voice")
+
+
+class DummyAlgorithm(Algorithm):
+    """This class is used to test all the possible functions of the tool chain,
+    but it does basically nothing."""
+
+    def __init__(self, **kwargs):
+        """Generates a test value that is read and written"""
+
+        # call base class constructor registering that this tool performs everything.
+        Algorithm.__init__(
+            self,
+            performs_projection=False,
+            requires_projector_training=False,
+            **kwargs
+        )
+
+    def score(self, toscore):
+        """Returns the evarage value of the probe"""
+        logger.info("score() score %f", toscore)
+
+        return toscore
+
+
+algorithm = DummyAlgorithm()

bob/pad/voice/algorithm/dummy_algorithm.py

-#!/usr/bin/env python
-# vim: set fileencoding=utf-8 :
-# @author: Pavel Korshunov <pavel.korshunov@idiap.ch>
-# @date: Wed 19 Oct 23:43:22 2016
-
-from bob.pad.base.algorithm import Algorithm
-
-import logging
-logger = logging.getLogger("bob.pad.voice")
-
-class DummyAlgorithm (Algorithm):
-  """This class is used to test all the possible functions of the tool chain, but it does basically nothing."""
-
-  def __init__(self, **kwargs):
-    """Generates a test value that is read and written"""
-
-    # call base class constructor registering that this tool performs everything.
-    Algorithm.__init__(
-        self,
-        performs_projection = False,
-        requires_projector_training = False,
-    )
-  
-  def score(self, toscore):
-    """Returns the evarage value of the probe"""
-    logger.info("score() score %f", toscore)
-    
-    return toscore
-
-algorithm = DummyAlgorithm()

bob/pad/voice/config/algorithm/normlogregr_algorithm.py → bob/pad/voice/config/algorithm/NormLogRegr.py

 
 import bob.pad.voice
 
-algorithm = bob.pad.voice.algorithm.LogRegrAlgorithm(
+algorithm = bob.pad.voice.algorithm.LogRegr(
     # use PCA to reduce dimension of features
     use_PCA_training = False,
     normalize_features = True,

bob/pad/voice/config/algorithm/pcalogregr_algorithm.py → bob/pad/voice/config/algorithm/PCALogRegr.py

 
 import bob.pad.voice
 
-algorithm = bob.pad.voice.algorithm.LogRegrAlgorithm(
+algorithm = bob.pad.voice.algorithm.LogRegr(
     # use PCA to reduce dimension of features
     use_PCA_training = True,
 )

bob/pad/voice/config/algorithm/gmm_scfc.py

 
 import bob.pad.voice
 
-algorithm = bob.pad.voice.algorithm.GmmAlgorithm(
+algorithm = bob.pad.voice.algorithm.GMM(
     number_of_gaussians = 512,
     kmeans_training_iterations = 10,   # Maximum number of iterations for K-Means
     gmm_training_iterations = 10,      # Maximum number of iterations for ML GMM Training

bob/pad/voice/test/test_spoofspeech.py

@@ -90,7 +90,7 @@ def test_spoof_EnergyLBP2():
         '-d', 'bob.pad.voice.test.dummy.database.DummyDatabaseSpeechSpoof()',
         '-p', 'bob.bio.spear.preprocessor.Mod_4Hz()',
         '-e', 'bob.pad.voice.extractor.LBPHistograms(features_processor=bob.pad.voice.extractor.SpectrogramExtended())',
-        '-a', 'bob.pad.voice.algorithm.LogRegrAlgorithm()',
+        '-a', 'bob.pad.voice.algorithm.LogRegr()',
         '-vs', 'test_energylbp',
         '--temp-directory', test_dir,
         '--result-directory', test_dir

setup.py

@@ -116,15 +116,15 @@ setup(
         ],
 
         'bob.pad.algorithm': [
-            'tensorflow  = bob.pad.voice.algorithm.tensorflow_algorithm:algorithm',
-            'dummy-algo  = bob.pad.voice.algorithm.dummy_algorithm:algorithm',
+            'tensorflow  = bob.pad.voice.algorithm.LSTMEval:algorithm',
+            'dummy-algo  = bob.pad.voice.algorithm.dummy:algorithm',
             # compute scores based on different energy bands
-            'logregr  = bob.pad.voice.algorithm.logregr_algorithm:algorithm',
-            'pcalogregr  = bob.pad.voice.config.algorithm.pcalogregr_algorithm:algorithm',
+            'logregr  = bob.pad.voice.algorithm.LogRegr:algorithm',
+            'pcalogregr  = bob.pad.voice.config.algorithm.PCALogRegr:algorithm',
             # the best performing LR classifier:
-            'normlogregr  = bob.pad.voice.config.algorithm.normlogregr_algorithm:algorithm',
-            'histdistance  = bob.pad.voice.algorithm.histdistance_algorithm:algorithm',
-            'gmm  = bob.pad.voice.algorithm.gmm_algorithm:algorithm',
+            'normlogregr  = bob.pad.voice.config.algorithm.NormLogRegr:algorithm',
+            'histdistance  = bob.pad.voice.algorithm.HistDistance:algorithm',
+            'gmm  = bob.pad.voice.algorithm.GMM:algorithm',
             # the same as above but with smaller thresholds
             'gmm-scfc  = bob.pad.voice.config.algorithm.gmm_scfc:algorithm',
         ],