当前位置: 首页>>代码示例>>Python>>正文


Python NervanaGPU.reciprocal方法代码示例

本文整理汇总了Python中nervanagpu.NervanaGPU.reciprocal方法的典型用法代码示例。如果您正苦于以下问题:Python NervanaGPU.reciprocal方法的具体用法?Python NervanaGPU.reciprocal怎么用?Python NervanaGPU.reciprocal使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在nervanagpu.NervanaGPU的用法示例。


在下文中一共展示了NervanaGPU.reciprocal方法的1个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: GPU

# 需要导入模块: from nervanagpu import NervanaGPU [as 别名]
# 或者: from nervanagpu.NervanaGPU import reciprocal [as 别名]

#.........这里部分代码省略.........
        return out

    def argmax(self, a, out, axis=0):
        """
        Calculates the indices of the maximal element value along the specified
        axis.  If multiple elements contain the maximum, only the elements of
        the first are returned.

        Arguments:
            tsr (GPUTensor): The GPUTensor on which to find the maximum indices
            axis (int): The dimension along which to find the maximum.  If set
                        to None, find the overall maximum index of a flattened
                        representation of tsr.
            out (GPUTensor): Where to store the result.  Should be of the
                             appropriate type and expected shape

        Returns:
            GPUTensor: reference to out
        """
        self.ng.argmax(a, out=out, axis=axis)
        return out

    def softmax(self, x, out):
        """
        Softmax nonlinearity. Computes exp(x-max(x)) / sum_i exp(x_i-max(x_i))

        Arguments:
            x (GPUTensor): input tensor.
            out (GPUTensor): where the result will be stored.

        Returns:
            GPUTensor: reference to out
        """
        out[:] = (self.ng.reciprocal(self.ng.sum(
                  self.ng.exp(x - self.ng.max(x, axis=0)), axis=0)) *
                  self.ng.exp(x - self.ng.max(x, axis=0)))
        return out

    def softmax_gradient(self, y, err, out):
        """
        Gradient of the softmax nonlinearity.

        Arguments:
            y (GPUTensor): input tensor.
            err (GPUTensor): backpropagated error.
            out (GPUTensor): where the result will be stored.

        Returns:
            GPUTensor: reference to out
        """
        raise NotImplementedError("Softmax gradient should use shortcut")
        return out

    def make_binary_mask(self, tsr, keepthresh=0.5, dtype=default_dtype):
        """
        Create a binary mask for dropout layers.

        Arguments:
            tsr (GPUTensor): Output tensor
            keepthresh (float): fraction of ones
        """
        self.ng.dropout(keep=keepthresh, out=tsr)

    def gdm_compound(self, ps_item, us_item, vs_item, momentum_coef,
                     learning_rate, epoch):
        """
开发者ID:YouVentures,项目名称:neon,代码行数:70,代码来源:gpu.py


注:本文中的nervanagpu.NervanaGPU.reciprocal方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。