Effacer les filtres
Effacer les filtres

My image size is of [566 804 3], what are the useful convolution filter sizes? How can I predict them? Every where I just given the same filter size and same number of filters?

1 vue (au cours des 30 derniers jours)
GUDIVADA ROKESH KUMAR
GUDIVADA ROKESH KUMAR le 16 Fév 2019
layers=[...
imageInputLayer([566 804 3])
convolution2dLayer(50, 20)
reluLayer
crossChannelNormalizationLayer(2)
maxPooling2dLayer(5,'stride',2,'padding',2)
convolution2dLayer(50, 20)
reluLayer
crossChannelNormalizationLayer(2)
maxPooling2dLayer(5,'stride',2,'padding',2)
convolution2dLayer(50, 20)
reluLayer
crossChannelNormalizationLayer(2)
maxPooling2dLayer(5,'stride',2,'padding',2)
convolution2dLayer(50, 20)
reluLayer
convolution2dLayer(50, 20)
reluLayer
convolution2dLayer(50, 20)
reluLayer
maxPooling2dLayer(5,'stride',2,'padding',2)
fullyConnectedLayer(2)
softmaxLayer
classificationLayer()]

Connectez-vous pour répondre à cette question.

Réponses (0)

Catégories

En savoir plus sur Image Data Workflows dans Help Center et File Exchange

Tags

Produits

Community Treasure Hunt

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

Start Hunting!

Translated by