x.grad_fn和x.requires_grad为x的属性x.grad_fn：积分方法名，默认为Nonex.requires_grad：是否积分的属性，默认为Falsex.requires_grad_()：设置积分的方法，设置之后requires_grad为True
"""Tensor"""
import torch
x = torch.ones(2, 2, requires_grad=True)
print(x)
print(x.grad_fn)
y = x + 2
print(y)
print(y.grad_fn)
print(x.is_leaf, y.is_leaf)
Processed:
0.009, SQL:
8
