Multiple softmax vectors in output layer of neural network using softmaxLayer
17 views (last 30 days)
Isuru Rathnayaka on 12 Dec 2021
I'm using deep learning toolbox in MATLAB 2021a. And the neural network that I'm trying to build has multiple softmax vectors in output layer. (e.g. 10 softmax vectors of length 8). That is, the calculation is similar to how in-built softmax() function applies to each column of a matrix.
>> a = randn(2,2)
However, I couldn't find a way to do this with softmaxLayer.
My code looks like this.
layersDNN = [
featureInputLayer(numInputs, 'Name', 'in')
fullyConnectedLayer(numInputs*2, 'Name', 'fc1')
fullyConnectedLayer(numInputs*8, 'Name', 'fc2')
I'm trying to get the softmaxLayer to divide numInputs*8 nodes in last layer to numInputs vectors of length 8 and apply softmax function separately.
Alternatively I'm trying to remove softmaxLayer and apply softmax to reshaped output of network. Something like this.
lgraphDNN = layerGraph(layersDNN);
dlnetDNN = dlnetwork(lgraphDNN);
out1 = forward(dlnetDNN, X);
out2 = reshape(out1, [numInputs, 8]);
pred = softmax(out2);
% calculate loss, gradients etc.
I'm not sure if this is a good solution. I'd like to know if there's a way to do this using softmaxLayer, since the requirement doesn't feel like an extreme case.
Prachi Kulkarni on 10 Jan 2022
Edited: Prachi Kulkarni on 12 Jan 2022
From the R2021b release onwards, you can create numInputs number of fully connected layers, each with output size 8. Every fully connected layer can then be connected to its own softmax layer.
The outputs from the softmax layers can be concatenated using a concatenation layer and then passed on to the output layer.
For more information, see the documentation for Concatenation layer.