MATLAB Answers

0

Problem creating network fitnet

Asked by Matthias Kuch on 27 Jun 2019
Hello,
i just wanted to start some pattern recognition using the DeepLearning Toolbox.
When i try to create a simple network, following the tutorial, i just get an error message.
This is my code:
[x,t] = simplefit_dataset;
net = fitnet(10);
Using these lines, i get the following error messages:
Not enough input arguments.
Error in minmax (line 3)
ymax = max(y);
Error in initnw>configure_layer_weight (line 117)
config.range = minmax(x);
Error in initnw (line 58)
out1 = configure_layer_weight(in2,in4,in5,in6);
Error in initlay>configure_layer_weight (line 126)
settings = feval(initFcn,'configure',net,'LW',i,j,x);
Error in initlay (line 55)
out1 = configure_layer_weight(in2,in4,in5,in6);
Error in nnet.internal.configure.layerWeight (line 26)
feval(net.initFcn,'configure',net,'LW',i,j,x);
Error in nnet.internal.configure.layer>iConfigurePreceedingLayerWeights (line 74)
net = nnet.internal.configure.layerWeight(net,i,j,inputRange);
Error in nnet.internal.configure.layer (line 25)
net = iConfigurePreceedingLayerWeights(net,i);
Error in network/subsasgn>setLayerInitFcn (line 1138)
net = nnet.internal.configure.layer(net,i,net.layers{i}.dimensions);
Error in network/subsasgn>network_subsasgn (line 192)
if isempty(err), [net,err] = setLayerInitFcn(net,i,initFcn); end
Error in network/subsasgn (line 14)
net = network_subsasgn(net,subscripts,v,netname);
Error in feedforwardnet>create_network (line 123)
net.layers{i}.initFcn = 'initnw';
Error in feedforwardnet (line 73)
net = create_network(param);
Error in fitnet>create_network (line 102)
net = feedforwardnet(param.hiddenSizes,param.trainFcn);
Error in fitnet (line 74)
net = create_network(param);
I already tried to reinstall the DeepLearning Toolbox, but it did not help.
Checking the licences, i get:
>> license('inuse')
distrib_computing_toolbox
matlab
neural_network_toolbox
statistics_toolbox
Can anyone help me? Thank you!

  0 Comments

Sign in to comment.

Products


Release

R2018b

0 Answers


Translated by