Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

图像复原能用热力图吗 #32

Open
ChangGuangyao opened this issue Dec 5, 2020 · 6 comments
Open

图像复原能用热力图吗 #32

ChangGuangyao opened this issue Dec 5, 2020 · 6 comments

Comments

@ChangGuangyao
Copy link

大佬您好 我是做图像复原的 请问热力图能应用到图像复原领域吗 如果可以的话,应该对谁进行反向传播呢 图像复原的结果是二维矩阵 并不是分类任务的一个值 求大佬指教

@yizt
Copy link
Owner

yizt commented Dec 9, 2020

@ChangGuangyao 您好,图像复原不熟悉,grad-cam本质是梯度的注意力,整张图也可以做反向传播

@ChangGuangyao
Copy link
Author

@ChangGuangyao您好,图像复原不熟悉,grad-cam本质是渐变的关注,整张图也可以做反向传播

反向传播不应该是一个值吗 二维的矩阵好像没法调用.backward()方法吧

@yizt
Copy link
Owner

yizt commented Dec 9, 2020

@ChangGuangyao 矩阵一样的可以反向传播的;例子如下:

x=torch.randn(3,3)
x.requires_grad_(True)
y=x*x
y.backward(torch.ones(3,3))
x.grad

@ChangGuangyao
Copy link
Author

@ChangGuangyao 矩阵一样的可以反向传播的;例子如下:

x=torch.randn(3,3)
x.requires_grad_(True)
y=x*x
y.backward(torch.ones(3,3))
x.grad

谢谢大佬

@darkmingy
Copy link

您好,我也是图像超分的方向,不知道您做出用热力图做出结果了吗?我尝试用grad-cam作图,但结果远不如分类和检测的展示效果好。不知道您的损失函数放的是什么呢?

@lander1003
Copy link

您好,我也是图像超分的方向,不知道您做出用热力图做出结果了吗?我尝试用grad-cam作图,但结果远不如分类和检测的展示效果好。不知道您的损失函数放的是什么呢?

您好,我目前也是用grad-cam做图像复原相关的grad-cam图,效果也是非常不好,请问你目前解决了吗

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants