We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
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。。
The text was updated successfully, but these errors were encountered:
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
Sorry, something went wrong.
明白,谢谢兄弟!
No branches or pull requests
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。。
The text was updated successfully, but these errors were encountered: