bob.machine.ISVMachine

All Samples(16) | Call(16) | Derive(0) | Import(0)

src/f/a/facereclib-1.2.1/facereclib/tools/ISV.py facereclib(Download)

      self._load_projector_isv(projector_file)
 
    self.m_machine = bob.machine.ISVMachine(self.m_isvbase)
    self.m_trainer = bob.trainer.ISVTrainer(self.m_isv_training_iterations, self.m_relevance_factor)
    self.m_trainer.rng = bob.core.random.mt19937(self.m_init_seed)

  def _project_isv(self, projected_ubm):
    projected_isv = numpy.ndarray(shape=(self.m_ubm.dim_c*self.m_ubm.dim_d,), dtype=numpy.float64)
    model = bob.machine.ISVMachine(self.m_isvbase)
    model.estimate_ux(projected_ubm, projected_isv)
    return projected_isv

  def read_model(self, model_file):
    """Reads the ISV Machine that holds the model"""
    machine = bob.machine.ISVMachine(bob.io.HDF5File(model_file))
    machine.isv_base = self.m_isvbase
    return machine

src/f/a/facereclib-HEAD/facereclib/tools/ISV.py facereclib(Download)

      self._load_projector_isv(projector_file)
 
    self.m_machine = bob.machine.ISVMachine(self.m_isvbase)
    self.m_trainer = bob.trainer.ISVTrainer(self.m_isv_training_iterations, self.m_relevance_factor)
    self.m_trainer.rng = bob.core.random.mt19937(self.m_init_seed)

  def _project_isv(self, projected_ubm):
    projected_isv = numpy.ndarray(shape=(self.m_ubm.dim_c*self.m_ubm.dim_d,), dtype=numpy.float64)
    model = bob.machine.ISVMachine(self.m_isvbase)
    model.estimate_ux(projected_ubm, projected_isv)
    return projected_isv

  def read_model(self, model_file):
    """Reads the ISV Machine that holds the model"""
    machine = bob.machine.ISVMachine(bob.io.HDF5File(model_file))
    machine.isv_base = self.m_isvbase
    return machine

src/x/b/xbob.spkrec-1.0.3/xbob/spkrec/tools/ISV.py xbob.spkrec(Download)

    self.m_isvbase.ubm = self.m_ubm
 
    self.m_machine = bob.machine.ISVMachine(self.m_isvbase)
    self.m_trainer = bob.trainer.ISVTrainer(self.m_config.n_iter_train, self.m_config.relevance_factor)

  def project_isv(self, feature_array, projected_ubm):
    #""Computes GMM statistics against a UBM, given an input 2D numpy.ndarray of feature vectors""
    projected_isv = numpy.ndarray(shape=(self.m_ubm.dim_c*self.m_ubm.dim_d,), dtype=numpy.float64)
 
    model = bob.machine.ISVMachine(self.m_isvbase)

  def read_model(self, model_file):
    """Reads the ISV Machine that holds the model"""
    print("model: %s" %model_file)
    machine = bob.machine.ISVMachine(bob.io.HDF5File(model_file))
    machine.isv_base = self.m_isvbase

src/b/o/bob.spear-1.1.2/spear/tools/ISV.py bob.spear(Download)

    self.m_isvbase.ubm = self.m_ubm
 
    self.m_machine = bob.machine.ISVMachine(self.m_isvbase)
    self.m_trainer = bob.trainer.ISVTrainer(self.m_config.n_iter_train, self.m_config.relevance_factor)

  def project_isv(self, feature_array, projected_ubm):
    #""Computes GMM statistics against a UBM, given an input 2D numpy.ndarray of feature vectors""
    projected_isv = numpy.ndarray(shape=(self.m_ubm.dim_c*self.m_ubm.dim_d,), dtype=numpy.float64)
 
    model = bob.machine.ISVMachine(self.m_isvbase)

  def read_model(self, model_file):
    """Reads the ISV Machine that holds the model"""
    print("model: %s" %model_file)
    machine = bob.machine.ISVMachine(bob.io.HDF5File(model_file))
    machine.isv_base = self.m_isvbase

src/x/b/xbob.thesis.elshafey2014-0.0.1a0/xbob/thesis/elshafey2014/utils/miris.py xbob.thesis.elshafey2014(Download)

 
  # 2/ ISV Enrollment
  isvmachine = bob.machine.ISVMachine(isvbase)
  isv_enrol_data = []
  data_c = data[ENROLLMENT_CLASS]

src/m/a/maskattack.study-1.0.0/maskattack/study/analyze/isv.py maskattack.study(Download)

    for j in range(0,len(array[0])):
      array_isv = numpy.ndarray(shape=(ubm.dim_c*ubm.dim_d,), dtype=numpy.float64)
      isv_machine = bob.machine.ISVMachine(isvbase)
      isv_machine.estimate_ux(array[i][j], array_isv)
      list.append(array_isv)

      for client_features in dev_enrol_dct_ubm:
        for enroll_feature in client_features:
          isv_machine = bob.machine.ISVMachine(isvbase)
          isv_trainer.enrol(isv_machine,[enroll_feature],1)
          dev_models.append(isv_machine)
 
      test_models = []
      for client_features in test_enrol_dct_ubm:
        for enroll_feature in client_features:
          isv_machine = bob.machine.ISVMachine(isvbase)