optimizer.py 文件源码

def accumulate_grads(self, grads):
        """Accumulates gradients from other source.

        This method just adds given gradient arrays to gradients that this
        optimizer holds. It is typically used in data-parallel optimization,
        where gradients for different shards are computed in parallel and
        aggregated by this method. This method correctly treats multiple GPU
        devices.

        Args:
            grads (Iterable): Iterable of gradient arrays to be accumulated.

        .. deprecated:: v1.5
           Use the :meth:`chainer.Link.addgrads` method of the target link
           instead.

        """
        for param, g_src in zip(self.target.params(), grads):
            g_dst = param.grad
            if isinstance(g_dst, numpy.ndarray):
                g_dst += cuda.to_cpu(g_src)
                continue

            with cuda.get_device(g_dst):
                if (isinstance(g_src, cuda.ndarray) and
                        g_dst.device != g_src.device):
                    g_dst += cuda.copy(g_src, out_device=g_dst.device)
                else:
                    g_dst += cuda.to_gpu(g_src)