pytorch中.data()與.item()

1..data()
將變量(Variable)變為tensor,將requires_grad設置為Flase

a = torch.tensor([1.0], requires_grad=True)
b = a.data
print(b, b.requires_grad)
## 輸出為： tensor([1.]) False

2..item()

a = torch.tensor([1.0], requires_grad=True)

c = a.item()
print(c, type(c))
## 輸出為：1.0 <class 'float'>