本文整理汇总了Python中nervanagpu.NervanaGPU.subtract方法的典型用法代码示例。如果您正苦于以下问题:Python NervanaGPU.subtract方法的具体用法?Python NervanaGPU.subtract怎么用?Python NervanaGPU.subtract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类nervanagpu.NervanaGPU
的用法示例。
在下文中一共展示了NervanaGPU.subtract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 subtract [as 别名]
#.........这里部分代码省略.........
ary (ndarray): Numpy array with source data
dtype (dtype, optional): Optional datatype
persist_values (bool, optional): If set to True (the default), the
values assigned to this Tensor
will persist across multiple begin
and end calls. Setting to False
may provide a performance increase
if values do not need to be
maintained across such calls
name (string): Name for the GPUTensor
allocator (pycuda): Pycuda memory allocator
Returns:
GPUTensor: output
"""
return GPUTensor(ary.shape, dtype, allocator=allocator, name=name,
rounding=self.ng.round_mode).set(ary)
def add(self, left, right, out):
"""
Elementwise addition
Arguments:
left (GPUTensor, numeric): left-hand side operand.
right (GPUTensor, numeric): right-hand side operand.
out (GPUTensor): where the result will be stored.
Returns:
GPUTensor: reference to out
"""
self.ng.add(left, right, out=out)
return out
def subtract(self, left, right, out):
"""
Elementwise subtraction
Arguments:
left (GPUTensor, numeric): left-hand side operand.
right (GPUTensor, numeric): right-hand side operand.
out (GPUTensor): where the result will be stored.
Returns:
GPUTensor: reference to out
"""
self.ng.subtract(left, right, out=out)
return out
def multiply(self, left, right, out):
"""
Elementwise multiplication
Arguments:
left (GPUTensor, numeric): left-hand side operand.
right (GPUTensor, numeric): right-hand side operand.
out (GPUTensor): where the result will be stored.
Returns:
GPUTensor: reference to out
"""
self.ng.multiply(left, right, out=out)
return out
def divide(self, left, right, out):
"""
Elementwise division