one of the variables needed for gradient computation has been modified by an inplace operation
import torch
import torch.optim
x = torch.tensor([3, 6], dtype=torch.float32)
x.requires_grad_(True)
optimizer = torch.optim.SGD([x], lr=0.1, momentum=0)
f = (x**2).sum()
for i in range(100):
optimizer.zero_grad()
f.backward(retain_graph=True)
.
原创
2022-03-09 22:16:09 ·
1055 阅读 ·
0 评论