torch.Tensor.requires_grad_

Tensor.requires_grad_(requires_grad=True) → Tensor

更改此张量上的 autograd 是否应记录操作：原地设置此张量的 requires_grad 属性。返回此张量。

requires_grad_() 的主要用例是告知 autograd 开始在张量 tensor 上记录操作。如果 tensor 的 requires_grad=False（因为它是由 DataLoader 提供的，或者需要预处理或初始化），则 tensor.requires_grad_() 会使 autograd 开始在 tensor 上记录操作。

参数

requires_grad (bool) – autograd 是否应在此张量上记录操作。默认为 True。

示例

>>> # Let's say we want to preprocess some saved weights and use
>>> # the result as new weights.
>>> saved_weights = [0.1, 0.2, 0.3, 0.25]
>>> loaded_weights = torch.tensor(saved_weights)
>>> weights = preprocess(loaded_weights)  # some function
>>> weights
tensor([-0.5503,  0.4926, -2.1158, -0.8303])

>>> # Now, start to record operations done to weights
>>> weights.requires_grad_()
>>> out = weights.pow(2).sum()
>>> out.backward()
>>> weights.grad
tensor([-1.1007,  0.9853, -4.2316, -1.6606])