MATLAB Answers

Dropout Layer Before Fully connected Layer

10 ビュー (過去 30 日間)
Abdussalam Elhanashi
Abdussalam Elhanashi 2020 年 1 月 17 日
コメント済み: Abdussalam Elhanashi 2020 年 1 月 26 日 19:37
Hi guys
I am asking if it is possible to make dropout layer before FC layer
Example below:-
layers = [
imageInputLayer([64 64 3],"Name","imageinput","Normalization","none")
convolution2dLayer([5 5],4,"Name","conv_1","Padding","same")
reluLayer("Name","relu_1")
maxPooling2dLayer([2 2],"Name","maxpool_1","Padding","same","Stride",[2 2])
convolution2dLayer([3 3],8,"Name","conv_2","Padding","same")
reluLayer("Name","relu_2")
maxPooling2dLayer([2 2],"Name","maxpool_2","Padding","same","Stride",[2 2])
convolution2dLayer([3 3],32,"Name","conv_3","Padding","same")
reluLayer("Name","relu_3")
averagePooling2dLayer([2 2],"Name","avgpool2d_1","Padding","same","Stride",[2 2])
convolution2dLayer([3 3],64,"Name","conv_4","Padding","same")
reluLayer("Name","relu_4")
averagePooling2dLayer([2 2],"Name","avgpool2d_2","Padding","same","Stride",[2 2])
dropoutLayer(0.51,'Name','drop1')
fullyConnectedLayer(2,"Name","fc")
softmaxLayer("Name","softmax")
classificationLayer("Name","classoutput")];
Best,

  0 件のコメント

サインイン to comment.

採用された回答

Shashank Gupta
Shashank Gupta 2020 年 1 月 20 日
Hi Abdussalam,
Yes, you can use Dropout layer before the fully connected layer, Dropout is just a regularization technique for preventing overfitting in the network, it can be applied anywhere regardless of FC or Conv but again it is generally recommended to use it after FC layer because they are the ones with the greater number of parameter and thus they are likely to excessively co-adapting themselves causing Overfitting.
However, it’s a stochastic regularization technique, you can really place it everywhere. Usually placed on the layer with a greater number of parameters, but no denies you from applying anywhere.

  1 件のコメント

Abdussalam Elhanashi
Abdussalam Elhanashi 2020 年 1 月 26 日 19:37
Hi Shashank Gupta
Thank For your reply
Is it possibe to use Dropout with value 0.6?
Best,

サインイン to comment.

その他の回答 (0 件)

サインイン してこの質問に回答します。

タグ


Translated by