Method backward_and_update

python/singa/opt.py:160–171

Performs backward propagation from the loss and parameter update. From the loss, it performs backward propagation to get the gradients and do the parameter update. Args: loss(Tensor): loss is the objective function of the deep learning model

(self, loss)

        "backward_and_update is deprecated, use __call__() to do update, refer to __call__ for more details."
    )
    def backward_and_update(self, loss):
        """Performs backward propagation from the loss and parameter update.

        From the loss, it performs backward propagation to get the gradients
        and do the parameter update.

        Args:
                loss(Tensor): loss is the objective function of the deep learning model
                optimization, e.g. for classification problem it can be the output of the
                softmax_cross_entropy function.
        """
        self.__call__(loss)


class SGD(Optimizer):