Cross entropy loss with label smoothing regularizer. Reference: Szegedy et al. Rethinking the Inception Architecture for Computer Vision. CVPR 2016. Equation: y = (1 - epsilon) * y + epsilon / K. Args: num_classes (int): number of classes. epsilon (float): weight.
source not stored for this graph (policy: none)
no outgoing calls
no test coverage detected
searching dependent graphs…