报错求助

[debug1818]

作者您好，请问你们有碰到这种报错吗？
Traceback (most recent call last):
File "train_our_policy.py", line 209, in
main(sys_args)
File "train_our_policy.py", line 156, in main
trainer.optimize_batch(num_batches, episode)
File "/home/user/GCRL-min-AoI/method/trainer.py", line 81, in optimize_batch
loss.backward()
File "/home/user/anaconda3/envs/mcs/lib/python3.8/site-packages/torch/_tensor.py", line 363, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
File "/home/user/anaconda3/envs/mcs/lib/python3.8/site-packages/torch/autograd/init.py", line 173, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [128, 61, 32]], which is output 0 of ReluBackward0, is at version 1; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).