cnn报错个人记录

1.RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [128, 128, 1]], which is output 0 of ReluBackward0, is at version 2; expected version 1 instead. Hint: enable anomaly det...

解决办法:

将网络中ReLU相关的激活函数中的(inplace=True)改为False。

你可能感兴趣的:(cnn,人工智能,神经网络)