dlgradient: Error Value to differentiate must be a traced dlarray scalar.
67 ビュー (過去 30 日間)
古いコメントを表示
I want to train a deep network by Automatic Differentiation. Is these any solution?
layer2 = [
imageInputLayer([9 36 1],'Normalization','none','Name','input1-fcc')
convolution2dLayer([7,7],64,'Name','conv1-fcc')
batchNormalizationLayer('Name','bn1-fcc')
reluLayer('Name','relu1-fcc')
globalAveragePooling2dLayer('Name','pool5-fcc')
fullyConnectedLayer(1,'Name','fc1')];
lgraph = layerGraph(layer2);
dlnet = dlnetwork(lgraph);
% Input
a = rand(9,36,1,10);
a = dlarray(a,'SSCB');
a_pre = forward(dlnet,a);
% output
b = rand(1,10);
loss = mse(a_pre,b);
gradients = dlgradient(loss,dlnet.Learnables);
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/488098/image.png)
0 件のコメント
採用された回答
Anshika Chaurasia
2021 年 1 月 18 日
Hi Qi Lu,
You can try following code to compute gradients that will resolve your error:
layer2 = [
imageInputLayer([9 36 1],'Normalization','none','Name','input1-fcc')
convolution2dLayer([7,7],64,'Name','conv1-fcc')
batchNormalizationLayer('Name','bn1-fcc')
reluLayer('Name','relu1-fcc')
globalAveragePooling2dLayer('Name','pool5-fcc')
fullyConnectedLayer(1,'Name','fc1')];
lgraph = layerGraph(layer2);
dlnet = dlnetwork(lgraph);
% Input
a = rand(9,36,1,10);
a = dlarray(a,'SSCB');
[loss,gradients] = dlfeval(@compute_gradient,dlnet,a);
function [loss,gradients]=compute_gradient(dlnet,a)
a_pre = forward(dlnet,a);
% output
b = rand(1,10);
loss = mse(a_pre,b);
gradients = dlgradient(dlarray(loss),dlnet.Learnables);%automatic gradient
end
Refer to the following documentation for more information on Automatic Differentiation.
0 件のコメント
その他の回答 (0 件)
参考
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!