torch.Tensor.requires_grad_

Tensor.requires_grad_(requires_grad=True) → Tensor

更改此張量是否應由 autograd 記錄操作：原地設定此張量的 requires_grad 屬性。返回此張量。

requires_grad_() 的主要用例是告訴 autograd 開始記錄對張量 tensor 的操作。如果 tensor 的 requires_grad=False（因為它透過 DataLoader 獲取，或需要預處理或初始化），呼叫 tensor.requires_grad_() 會使得 autograd 開始記錄對 tensor 的操作。

引數

requires_grad (bool) – 如果 autograd 應該記錄對此張量的操作。預設值：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])