本文整理汇总了Python中torch.autograd.Variable.matmul方法的典型用法代码示例。如果您正苦于以下问题：Python Variable.matmul方法的具体用法？Python Variable.matmul怎么用？Python Variable.matmul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torch.autograd.Variable的用法示例。
在下文中一共展示了Variable.matmul方法的2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: test_matmul_native
# 需要导入模块: from torch.autograd import Variable [as 别名]
# 或者: from torch.autograd.Variable import matmul [as 别名]
def test_matmul_native(self):
x = Variable(torch.Tensor([[0.4]]), requires_grad=True)
y = Variable(torch.Tensor([[0.7]]), requires_grad=True)
trace, z = torch.jit.trace(lambda x, y: x.matmul(y), (x, y), nderivs=0)
torch._C._jit_pass_lint(trace)
torch._C._jit_pass_dce(trace)
self.assertExpectedTrace(trace)示例2: test_constant
# 需要导入模块: from torch.autograd import Variable [as 别名]
# 或者: from torch.autograd.Variable import matmul [as 别名]
def test_constant(self):
x = Variable(torch.randn(2, 2), requires_grad=True)
trace = torch._C._tracer_enter((x,), 0)
y = Variable(torch.diag(torch.Tensor([2, 2])))
z = x.matmul(y)
torch._C._tracer_exit((z,))
function = torch._C._jit_createAutogradClosure(trace)
z2 = function()(x)
self.assertEqual(z, z2)
y.data.fill_(1000) # make sure the data has been cloned
x2 = Variable(torch.ones(2, 2) * 2, requires_grad=True)
z3 = function()(x2)
self.assertEqual(z3.data, torch.ones(2, 2) * 4)