nondefaced_detector.models.model.CombinedClassifier

CombinedClassifier(input_shape=(32, 32), dropout=0.4, wts_root=None, trainable=False, shared=False)[source]

The final block of the model that combines features and outputs a real-valued probability using the sigmoid function.

Parameters

  • input_shape (tuple of ints, default=(32, 32)) – The shape of the input image.

  • dropout (float, optional, default=0.4) – Float between 0 and 1. Fraction of the input units to drop.

  • trainable (bool, default=True) – If True, the model is set to be trainable else the model layers are frozen.

  • shared (bool, default=False) –