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

fcn模型结构 #6

Closed
kingofoz opened this issue Feb 24, 2018 · 2 comments
Closed

fcn模型结构 #6

kingofoz opened this issue Feb 24, 2018 · 2 comments

Comments

@kingofoz
Copy link

你好,
我在看您博客上介绍fcn的那篇文章,有个地方不太懂,特来讨教:
最简单的 fcn 前面是一个去掉全连接层的预训练网络,然后将去掉的全连接变为 1x1 的卷积,输出和类别数目相同的通道数,比如 voc 数据集是 21 分类,那么输出的通道数就是 21,然后最后接一个转置卷积将结果变成输入的形状大小,最后在每个 pixel 上做一个分类问题,使用交叉熵作为损失函数就可以了。

通道数为什么也得是21,这个地方不太懂。。

@L1aoXingyu
Copy link
Owner

通道数就像是分类数目,比如输入图片是 100x100,30 分类,那么输出就应该是 30x100x100,在每个像素点上做分类,所以通道数需要和类别数一样

@kingofoz
Copy link
Author

明白,谢谢兄弟!

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

2 participants