Training problem

[xch1176411706]

Traceback (most recent call last):
File "train.py", line 255, in
main(sys_args)
File "train.py", line 156, in main
trainer.optimize_epoch(il_epochs)
File "/home/xuech23/Code/RelationalGraphLearning/crowd_nav/utils/trainer.py", line 83, in optimize_epoch
loss.backward()
File "/home/xuech23/anaconda3/envs/python3.7/lib/python3.7/site-packages/torch/_tensor.py", line 489, in backward
self, gradient, retain_graph, create_graph, inputs=inputs
File "/home/xuech23/anaconda3/envs/python3.7/lib/python3.7/site-packages/torch/autograd/init.py", line 199, in backward
allow_unreachable=True, accumulate_grad=True) # 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.FloatTensor [100, 6, 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).

Hello, what is the reason for this problem? I also tried to change the python version and the gym version, but this problem always exists. I am looking forward to your answer

thank you