RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [256, 1]], which is output 0 of AsStridedBackward0, is at version 2; expected version 1 instead. Hint: enable anomaly detRuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [256, 1]], which is output 0 of AsStridedBackward0, is at version 2; expected version 1 instead. Hint: with torch.autograd.set_detect_anomaly(True).
解决办法torch降级,torch==1.4,具体报错原因不知