记录实验过程中遇到的问题
2022/4/3:oac
报错
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [256, 1]], which is output 0 of AsStridedBackward0, is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).
Process finished with exit code 1
之前没问题,忽然一天就报错,但是我没有动过环境和代码。torch 版本 是1.10.2
解决方法
torch 版本换为1.4.0
这个操作就很迷,之前不知道为啥能跑通,是在我不知道的时候,自己换版本了?
2022/4/4 : oc
报错
expected object of device type cuda but got device type cpu for argument #1