def forward()

in losses.py [0:0]

• 28 lines of code
• 5 McCabe index (conditional complexity)

    def forward(self, inputs, outputs, labels):
        """
        Args:
            inputs: The original inputs that are feed to the teacher model
            outputs: the outputs of the model to be trained. It is expected to be
                either a Tensor, or a Tuple[Tensor, Tensor], with the original output
                in the first position and the distillation predictions as the second output
            labels: the labels for the base criterion
        """
        outputs_kd = None
        if not isinstance(outputs, torch.Tensor):
            # assume that the model outputs a tuple of [outputs, outputs_kd]
            outputs, outputs_kd = outputs

        if isinstance(outputs, tuple):
            base_loss = self.base_criterion(outputs, labels, inputs)
        else:
            base_loss = self.base_criterion(outputs, labels)

        if self.distillation_type == 'none':
            return base_loss

        if outputs_kd is None:
            raise ValueError("When knowledge distillation is enabled, the model is "
                             "expected to return a Tuple[Tensor, Tensor] with the output of the "
                             "class_token and the dist_token")
        # don't backprop throught the teacher
        with torch.no_grad():
            teacher_outputs = self.teacher_model(inputs)

        if self.distillation_type == 'soft':
            T = self.tau
            # taken from https://github.com/peterliht/knowledge-distillation-pytorch/blob/master/model/net.py#L100
            # with slight modifications
            distillation_loss = F.kl_div(
                F.log_softmax(outputs_kd / T, dim=1),
                F.log_softmax(teacher_outputs / T, dim=1),
                reduction='sum',
                log_target=True
            ) * (T * T) / outputs_kd.numel()
        elif self.distillation_type == 'hard':
            distillation_loss = F.cross_entropy(outputs_kd, teacher_outputs.argmax(dim=1))

        loss = base_loss * (1 - self.alpha) + distillation_loss * self.alpha
        return loss