在使用Grad-CAM时遇到RuntimeError，该错误通常发生在尝试就地修改返回的视图上。解决方案是将可能导致就地修改的ReLU层的`inplace`参数设为`False`，例如将`nn.ReLU(inplace=True)`改为`nn.ReLU()`。这将避免自定义反向传播逻辑与PyTorch内部视图处理之间的冲突，确保正确计算梯度。
RuntimeError: Output 0 of BackwardHookFunctionBackward is a view and is being modified inplace. This view was created inside a custom Function (or because an input was returned as-is) and the autograd logic to handle view+inplace would override the custom backward associated with the custom Function, leading to incorrect gradients. This behavior is forbidden. You can fix this by cloning the output of the custom Function.
使用grad_cam 时报错了
参考如下：
https://discuss.pytorch.org/t/getting-this-warning-output-0-of-backwardhookfunctionbackward-is-a-view-and-is-being-modified-inplace/122766
激活函数的问题。
将self.relu1 = nn.ReLU(inplace=True) 改为： self.relu1 = nn.ReLU()
即可
扫一扫
4643
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
