Training Network stopping automatically after 3 iteration without showing any error.

28 ビュー (過去 30 日間)
Aravind Mallemputi
Aravind Mallemputi 2021 年 11 月 30 日
コメント済み: Image Analyst 2022 年 4 月 5 日
tspan = 0:0.001:10;
y0 = 0;
[t,y] = ode45(@(t,y) t^2+2, tspan, y0);
T=t(1:0.9*end)
Y=y(1:0.9*end)
x=t(0.9*end+1:end)
v=y(1+0.9*end:end)
layer = functionLayer((@(X) X./(1 -X^2)))
layers = [
sequenceInputLayer(1)
fullyConnectedLayer(1)
tanhLayer
functionLayer(((@(t) t./(1 -t.^2))),Description="softsign")
fullyConnectedLayer(1)
tanhLayer
functionLayer(((@(t) t./(1 -t.^2))),Description="softsign")
regressionLayer]
options = trainingOptions('adam', ...
'LearnRateSchedule','piecewise', ...
'LearnRateDropFactor',0.2, ...
'LearnRateDropPeriod',5, ...
'miniBatchSize',20,.....
'VerboseFrequency',1,...
'ValidationPatience',Inf,...
'MaxEpochs',100, ...
'Plots','training-progress')
net = trainNetwork(T',Y',layers,options);
ypre=predict(net,tspan);
plot(ypre)
plot(y)

回答 (1 件)

Prateek Rai
Prateek Rai 2022 年 2 月 22 日
Hi,
Training of the network stopped because training loss is NaN. This implies that the predictions using the output network might contain NaN values.
On analyzing network, I found that size of the all the layers is 1*1*1 which is why NaN values are coming.
You might want to recheck the dimension of the layers of the network using:
analyzeNetwork(layers)
  1 件のコメント
Image Analyst
Image Analyst 2022 年 4 月 5 日
I get the same error trying to train on 448 images and my layers are not 1*1*1 -- they're 227x227x3

サインインしてコメントする。

製品


リリース

R2021b

Community Treasure Hunt

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

Start Hunting!

Translated by