enable_grad

class torch.enable_grad(orig_func=None)

Context-manager that enables gradient calculation.

Enables gradient calculation, if it has been disabled via no_grad or set_grad_enabled.

此上下文管理器是线程局部（thread local）的；它不会影响其他线程中的计算。

也可作为装饰器使用。

注意

enable_grad is one of several mechanisms that can enable or disable gradients locally see Locally disabling gradient computation for more information on how they compare.

注意

此 API 不适用于前向模式 AD。

示例：

>>> x = torch.tensor([1.], requires_grad=True)
>>> with torch.no_grad():
...     with torch.enable_grad():
...         y = x * 2
>>> y.requires_grad
True
>>> y.backward()
>>> x.grad
tensor([2.])
>>> @torch.enable_grad()
... def doubler(x):
...     return x * 2
>>> with torch.no_grad():
...     z = doubler(x)
>>> z.requires_grad
True
>>> @torch.enable_grad()
... def tripler(x):
...     return x * 3
>>> with torch.no_grad():
...     z = tripler(x)
>>> z.requires_grad
True