torch.Tensor.requires_grad_

Tensor.requires_grad_(requires_grad=True) → Tensor

變更 autograd 是否應在此 tensor 上記錄運算：就地設定此 tensor 的 requires_grad 屬性。傳回此 tensor。

requires_grad_() 的主要用例是告訴 autograd 開始記錄 Tensor tensor 上的運算。 如果 tensor 具有 requires_grad=False（因為它是透過 DataLoader 取得，或是需要預處理或初始化），則 tensor.requires_grad_() 會使 autograd 開始記錄 tensor 上的運算。

參數

requires_grad (bool) – 如果 autograd 應該記錄此張量上的運算。預設值：True。

範例

>>> # 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])