当前位置: 首页>>代码示例>>Python>>正文


Python Connector.assign_sequential_weighted_sum方法代码示例

本文整理汇总了Python中quagga.connector.Connector.assign_sequential_weighted_sum方法的典型用法代码示例。如果您正苦于以下问题:Python Connector.assign_sequential_weighted_sum方法的具体用法?Python Connector.assign_sequential_weighted_sum怎么用?Python Connector.assign_sequential_weighted_sum使用的例子?那么, 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quagga.connector.Connector的用法示例。


在下文中一共展示了Connector.assign_sequential_weighted_sum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: AttentionBlock

# 需要导入模块: from quagga.connector import Connector [as 别名]
# 或者: from quagga.connector.Connector import assign_sequential_weighted_sum [as 别名]
class AttentionBlock(object):
    """
    Location based attention block
    out = sum_{i=1}^{T}a_i * h_i
    a_i = softmax(h_i * u)
    """
    def __init__(self, matrices, u, mask=None, device_id=None):
        self.context = Context(device_id)
        device_id = self.context.device_id
        self.output = Matrix.empty_like(matrices[0], device_id)
        learning = matrices[0].bpropagable or u.bpropagable
        self.output = Connector(self.output, device_id if learning else None)
        if matrices[0].bpropagable:
            self.matrices, self.dL_dmatrices = \
                izip(*matrices.register_usage(device_id, device_id))
        else:
            self.matrices = matrices.register_usage(device_id)
        self.length = matrices.length
        if u.bpropagable:
            self.u, self.dL_du = u.register_usage(device_id, device_id)
        else:
            self.u = u.register_usage(device_id)
        if mask:
            self.mask = mask.register_usage(device_id)
        self.a = Matrix.empty(matrices[0].nrows, matrices.length,
                              'float', device_id)
        self.dL_dpre_a = Matrix.empty_like(self.a)
        self.a_cols = [self.a[:, i] for i in xrange(len(self.matrices))]

    def fprop(self):
        for i in xrange(self.length):
            self.a_cols[i].assign_dot(self.context, self.matrices[i], self.u)
        if hasattr(self, 'mask'):
            self.a.fill(self.context, -3.402823466e+38, self.mask, 0.0)
        self.a.softmax(self.context, self.a)
        self.output.assign_sequential_weighted_sum(self.context, self.a,
                                                   self.matrices[:self.length])
        self.output.fprop()

    def bprop(self):
        dL_doutput = self.output.backward_matrix
        self.dL_dpre_a.assign_dL_dpre_a(self.context, dL_doutput, self.a,
                                        self.matrices[:self.length])
        if hasattr(self, 'dL_dmatrices'):
            Matrix.add_attention_tile(self.context, dL_doutput, self.a,
                                      self.dL_dpre_a, self.u,
                                      self.dL_dmatrices[:self.length])
        if hasattr(self, 'dL_du'):
            self.dL_du.add_attention_derivative(self.context, self.dL_dpre_a,
                                                self.matrices[:self.length])
开发者ID:Sandy4321,项目名称:quagga,代码行数:52,代码来源:AttentionBlock.py


注:本文中的quagga.connector.Connector.assign_sequential_weighted_sum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。