Loss can't backward

[Originofamonia]

Hi, I encountered an issue that the loss can't backward. It seems there is an operation to modify a tensor inplace, but I can't find where is it. Could you please look into it?
Here is the stacktrace:
Traceback (most recent call last):
File "/home/qiyuan/2021summer/VQA_ReGAT/main.py", line 275, in
main()
File "/home/qiyuan/2021summer/VQA_ReGAT/main.py", line 271, in main
train(model, train_loader, eval_loader, args, device)
File "/home/qiyuan/2021summer/VQA_ReGAT/train.py", line 111, in train
loss.backward()
File "/home/qiyuan/miniconda3/envs/torch14/lib/python3.8/site-packages/torch/tensor.py", line 195, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/home/qiyuan/miniconda3/envs/torch14/lib/python3.8/site-packages/torch/autograd/init.py", line 97, in backward
Variable._execution_engine.run_backward(
RuntimeError: unsupported operation: more than one element of the written-to tensor refers to a single memory location. Please clone() the tensor before performing the operation.
0%| | 0/3467 [00:04<?, ?it/s]

Process finished with exit code 1

Thanks.

[Originofamonia]

Nevermind, it's been solved by adding clone() to where have expand().

[jhss]

While running your fork code, I have similar problem.

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [64, 2048]], which is output 0 of ReluBackward0, is at version 1; expected version 0 instead.

I changed all ReLU inplace = False, but I couldn't solve it.
Could you let me know the way to solve the problem?