Using word embedding layer and convolutional layer

2021 8 26
0 个回答
更新时间：2021 9 15
9 次查看（30 天）

0 个投票

Hello everyone. I'm new to use MATLAB. i had to implement a neural network described in keras in MATLAB for a project. I have to use various layer such as wordembedding layer and convolutional layer. i don't understand if the wordembedding layer of matlab equals the embedding layer of keras. As input i have sequence of 200 amino acids. Using deep network designer I built this net but it keep giving me error in the convolutional layer because there is a mismatch.
lgraph = layerGraph();
tempLayers = [
sequenceInputLayer(1,"Name","sequence")
wordEmbeddingLayer(128,3,"Name","word-embedding")
sequenceFoldingLayer("Name","seqfold")];
reluLayer
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
convolution2dLayer([1 16],64,"Name","conv","BiasInitializer","narrow-normal","Padding","same","Stride",1)
batchNormalizationLayer("Name","batchnorm")
reluLayer("Name","relu")
maxPooling2dLayer([5 1],"Name","maxpool","Padding","same")
];
lgraph = addLayers(lgraph,tempLayers);
tempLayers = [
sequenceUnfoldingLayer("Name","sequnfold")
flattenLayer("Name","flatten")
lstmLayer(100,"Name","lstm","OutputMode","last")
dropoutLayer(0.1,"Name","dropout")
%fullyConnectedLayer(numClasses)
sigmoidLayer("Name","sigmoid")
softmaxLayer("Name","softmax")
classificationLayer("Name","classoutput")];
lgraph = addLayers(lgraph,tempLayers);
lgraph = connectLayers(lgraph,"seqfold/out","conv");
lgraph = connectLayers(lgraph,"seqfold/miniBatchSize","sequnfold/miniBatchSize");
lgraph = connectLayers(lgraph,"maxpool","sequnfold/in");

请先登录，再回答此问题。

回答（0 个）

类别

在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

产品

版本

R2021a

标签

Community Treasure Hunt

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

Start Hunting!

Translated by