how to define a fully convolution net?

Question

QU HAIFENG 2018-6-7

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/404456-how-to-define-a-fully-convolution-net

编辑： Matt J 2022-4-27

I'm trying to build a FCN to segment image, so how to define my input layer using imageInputLayer function ,dose it seems like imageInputLayer(auto, auto, 3)?

2 个评论
显示无隐藏无

QU HAIFENG 2018-6-7

Maybe I don't describe the problem clearly, I want to input arbitrary size image to my convolution net, tkz for any suggestion.

Matt J 2022-4-27

编辑：Matt J 2022-4-27

Yes! How?? It's shockingly difficult to get clarification on how to do this.

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

QU HAIFENG 2018-6-7

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/404456-how-to-define-a-fully-convolution-net#answer_323576

I found answer from document --Semantic Segmentation Examples: "A semantic segmentation network starts with an imageInputLayer, which defines the smallest image size the network can process. Most semantic segmentation networks are fully convolutional, which means they can process images that are larger than the specified input size. Here, an image size of [32 32 3] is used for the network to process 64x64 RGB images."

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Matt J 2022-4-27

编辑：Matt J 2022-4-27

That's good to know, but the imageInputLayer performs operations on the inputs that are not convolutional or shift invariant. Doesn't that defeat the goal of achieving an FCN? Or did you turn off all the normalizations?

请先登录，再进行评论。