Error when running patternnet example code from Help documentation
2 次查看(过去 30 天)
显示 更早的评论
I am attempting to run the example code from the Help documentation for function patternnet:
[x,t] = iris_dataset;
net = patternnet(10);
net = train(net,x,t);
view(net)
y = net(x);
perf = perform(net,t,y);
classes = vec2ind(y);
I get an error in the command window when when I try to run patternnet(10):
Error using boiler_transfer (line 98)
Unrecognized code: 'defaultParam'
Error in softmax (line 75)
boiler_transfer
Error in network/subsasgn>getDefaultParam (line 2048)
param = struct(feval(fcn,'defaultParam'));
Error in network/subsasgn>setLayerTransferFcn (line 1224)
net.layers{i}.transferParam = getDefaultParam(transferFcn);
Error in network/subsasgn>network_subsasgn (line 208)
if isempty(err), [net,err] = setLayerTransferFcn(net,i,transferFcn); end
Error in network/subsasgn (line 13)
net = network_subsasgn(net,subscripts,v,netname);
Error in patternnet>create_network (line 104)
net.layers{net.numLayers}.transferFcn = 'softmax';
Error in patternnet (line 71)
net = create_network(param);
Can anyone shed some light on what is going wrong? I am running Matlab 2014a.
Regards
Bob
0 个评论
采纳的回答
Siddharth Sundar
2014-10-14
编辑:Siddharth Sundar
2014-10-14
From the error, it looks like you could have another function softmax that shadows the one shipped with the product. So you might want to try the which command:
which -all softmax
If this lists more than the softmax at the location 'toolbox\nnet\nnet\nntransfer\softmax.m', you might want to remove the other softmax.m from your path before using the patternnet function.
3 个评论
Jason Potas
2016-11-22
Awesome thanks, that was also my issue; a deep learning toolbox also had a softmax function in a different path, so by removing it from the set paths it now works fine.
更多回答(1 个)
Greg Heath
2014-10-14
The only thing that I can think of is to use clear or clear all before using those 7 commands.
0 个评论
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!