Hellow，I ran the train.py file but encountered the following problem.How do I fix it?
dataset is HT21, images num is 5312
train/HT21-01
Using /home/liuwenjie/.cache/torch_extensions/py38_cu118 as PyTorch extensions root...
Detected CUDA files, patching ldflags
Emitting ninja build file /home/liuwenjie/.cache/torch_extensions/py38_cu118/_prroi_pooling/build.ninja...
Building extension module _prroi_pooling...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
ninja: no work to do.
Loading extension module _prroi_pooling...
Traceback (most recent call last):
File "train.py", line 313, in
cc_trainer.forward()
File "train.py", line 50, in forward
self.train()
File "train.py", line 86, in train
all_loss.backward()
File "/home/liuwenjie/anaconda3/envs/DRNet2/lib/python3.8/site-packages/torch/_tensor.py", line 487, in backward
torch.autograd.backward(
File "/home/liuwenjie/anaconda3/envs/DRNet2/lib/python3.8/site-packages/torch/autograd/init.py", line 200, 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 [4, 128, 96, 128]], 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).
taohan10200
