How to convert the format of data from sequences to matrices when designing deep learning networks?

12 次查看（过去 30 天）

Tian,HCong 2024-5-30

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2123971-how-to-convert-the-format-of-data-from-sequences-to-matrices-when-designing-deep-learning-networks

评论： Tian,HCong 2024-6-2

Hello,

After importing the network into DeepNetworkDesigner for analysis, I encountered the following problem: after being processed by selfattentionLayer, the data size format is 577 (S) x 577 (C) x 1 (B).

I want to convert it to a format similar to imageInputLayer, _ (S) x_ (S) x_ (C) x_ (B). How can I use MATLAB to implement it?

The code for the network is as follows:

patchSize = 16;
embeddingOutputSize = 768;
layer = patchEmbeddingLayer(patchSize,embeddingOutputSize)
net = dlnetwork;
inputSize = [384 384 3];
maxPosition = (inputSize(1)/patchSize)^2 + 1;
numHeads = 4;
numKeyChannels = 4*embeddingOutputSize;
numClasses = 1000;
layers = [ 
    imageInputLayer(inputSize)
    patchEmbeddingLayer(patchSize,embeddingOutputSize,Name="patch-emb")
    embeddingConcatenationLayer(Name="emb-cat")
    positionEmbeddingLayer(embeddingOutputSize,maxPosition,Name="pos-emb");
    additionLayer(2,Name="add")
    selfAttentionLayer(numHeads,numKeyChannels,AttentionMask="causal",OutputSize=maxPosition)
    fullyConnectedLayer(numClasses)
    softmaxLayer];
net = addLayers(net,layers);
net = connectLayers(net,"emb-cat","add/in2");