MATLAB Answers

Lee
0

Error when training a neural network with more than 1 dimension

Asked by Lee
on 24 Aug 2018
Latest activity Commented on by Lee
on 10 Sep 2018
I have a neural network license, and am able to execute the first two examples found in the Matlab documentation here: https://ch.mathworks.com/help/nnet/ref/train.html
These use the builtin 'maglev_dataset', which is 1 dimensional. However, the other examples using the 'vinyl_dataset', which has more than 1 dimension, all throw the following error immediately.
>> [x,t] = vinyl_dataset;
>> net = fitnet([60 30]);
>> net = train(net,x,t);
Index exceeds matrix dimensions.
Error in initnw>initialize_layer (line 168)
range(inputStart(j):inputStop(j),:) = temp2((inputStart(j):inputStop(j))-inputStart(j)+1,:);
Error in initnw (line 93)
out1 = initialize_layer(in1,in2);
Error in initlay>initialize_network (line 147)
net = feval(initFcn,net,i);
Error in initlay (line 89)
out1 = initialize_network(in1);
Error in network/init (line 32)
net = feval(initFcn,net);
Error in network/configure (line 246)
net = init(net);
Error in nntraining.config (line 116)
net = configure(network(net),X,T);
Error in nntraining.setup>setupPerWorker (line 68)
[net,X,Xi,Ai,T,EW,Q,TS,err] = nntraining.config(net,X,Xi,Ai,T,EW,configNetEnable);
Error in nntraining.setup (line 43)
[net,data,tr,err] = setupPerWorker(net,trainFcn,X,Xi,Ai,T,EW,enableConfigure);
Error in network/train (line 321)
[net,data,tr,err] = nntraining.setup(net,net.trainFcn,X,Xi,Ai,T,EW,enableConfigure,isComposite);
What on earth is wrong? My colleagues who use the same license do not have this problem!

  2 Comments

Could you try running restoredefaultpath, and check again?
Thank you! it was indeed a path issue, and I've reordered it accordingly.

Sign in to comment.

Products


Release

R2014b

0 Answers