how to define a fully convolution net?

2 vues (au cours des 30 derniers jours)
QU HAIFENG
QU HAIFENG le 7 Juin 2018
Modifié(e) : Matt J le 27 Avr 2022
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 commentaires
QU HAIFENG
QU HAIFENG le 7 Juin 2018
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
Matt J le 27 Avr 2022
Modifié(e) : Matt J le 27 Avr 2022
Yes! How?? It's shockingly difficult to get clarification on how to do this.

Connectez-vous pour commenter.

Réponse acceptée

QU HAIFENG
QU HAIFENG le 7 Juin 2018
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 commentaire
Matt J
Matt J le 27 Avr 2022
Modifié(e) : Matt J le 27 Avr 2022
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?

Connectez-vous pour commenter.

Plus de réponses (0)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by