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

조회 수: 9(최근 30일)
Aravind Mallemputi 2021년 11월 30일
댓글: Image Analyst 2022년 4월 5일 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]
'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)

댓글을 달려면 로그인하십시오.

### 답변(1개)

Prateek Rai 2022년 2월 22일
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)
##### 댓글 수: 1표시숨기기 없음
Image Analyst 2022년 4월 5일
I get the same error trying to train on 448 images and my layers are not 1*1*1 -- they're 227x227x3 댓글을 달려면 로그인하십시오.

R2021b

### Community Treasure Hunt

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

Start Hunting!