one of the variables needed for gradient computation has been modified by an inplace operation

[miaoshuyu]

Traceback (most recent call last): File "train_test.py", line 454, in train() File "train_test.py", line 327, in train loss.backward() File "/home/miao/anaconda3/lib/python3.6/site-packages/torch/tensor.py", line 93, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "/home/miao/anaconda3/lib/python3.6/site-packages/torch/autograd/init.py", line 90, in backward allow_unreachable=True) # allow_unreachable flag RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation

when i run python train_test.py, i met this problem.How can i solve it.

[miaoshuyu]

The problem has been solved: in layers/modules/l2norm.py x /= norm to: x = x / norm

[DonghoonPark12]

x = torch.div(x,norm) is also okay.