Hi,感谢你们这么棒的工作,我在运行test.py没有问题,但是运行demo.py会出现:
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [324, 3, 3]], which is output 0 of ViewBackward, is at version 37; expected version 35 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True)
请问这是因为IK的关系才会出现这样的错误吗?
Hi,感谢你们这么棒的工作,我在运行test.py没有问题,但是运行demo.py会出现: RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [324, 3, 3]], which is output 0 of ViewBackward, is at version 37; expected version 35 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True) 请问这是因为IK的关系才会出现这样的错误吗?