How to get the gradient with respect to the output of a specific layer in a deep learning model?
11 visualizzazioni (ultimi 30 giorni)
I have a model myModel which is a simple 2 Layers model (i.e. input size: 3; Layer_1 size: 7; Layer_2 size: 4).
That is, the layer's output is a and the loss is .
From below code, now I have the whose dimention is 60 since there are 60 parameters in the model (i.e. (3+1)*7+(7+1)*4 = 60). Nis the number of data points (i.e. in my code)
But want I want is the gradient with respect to the layer 2's output, instead of the loss. That is, I want instead, whose dimention would be since .
How can I get ? Many thanks!
rng(123); % seed
X_ori=[4,163,80;5,164,75]; % data; #(number) = 2; #(features) = 3;
dlX = dlarray(X, 'SSCB');
Y_ori=[0, 0, 0, 1; 0, 1, 0, 0]; % data labels (i.e. one-hot vectors for 4 classes)
myModel = [
imageInputLayer([1 1 3],'Normalization','none','Name','in')
MyLGraph = layerGraph(myModel);
myDLnet = dlnetwork(MyLGraph);
gradients = dlfeval(@modelGradients, myDLnet, dlX, Y_ori);
function [gradients] = modelGradients(myModel, modelInput, CorrectLabels)
[modelOutput,state] = forward(myModel,modelInput);
loss = -sum(sum(CorrectLabels_transpose.*log(sigmoid(modelOutput/100))));
gradients = dlgradient(loss, myModel.Learnables);
Athul Prakash il 25 Nov 2019
You could try looking at the source code for the fullyConnectedLayer that you're using; and then customizing that code to return the gradients you're looking for.
Alternatively, try creating your own custom layer to achieve this. See the doc below for that:
Hope it Helps!