I have been using matlab's neural network toolbox lately for my research. I created some neural networks using fitting tool of this toolbox. Now I encountered a problem while testing the network with new data. Basically, I want to test the network with some new data, which do not have the same sample number as the network. For example, I have created the network with the input of 12x36 matrix (12 variables, 36 samples) and output of 1x36 vector (1 variable, 36 samples). Now, I want to get the results for a new data (12x11520 (12 variables and 11520 samples)). However, when I put this data into the network and get the results, I only get an output vector of 1x36 (1 variable 36 samples) while I was expecting to get the results as 1x11520 (1 variable and 11520 samples). I am using the below line to get the results from the neural network named as network.
output_estimate = network(input');
I also tried the line below to get the results but the result did not change.
output_estimate = sim(network,input');
Could you please help me understand this and get the output as the same sample length so that I can compare the expected and actual results for the new data.
Thank you very much in advance.
Irem
Related
I have two sets of 58 images each which I have to feed as input to a multiple-input network.
To do so, I first read each of the sets onto a different Image Datastore, as shown on the images
Reading the first dataset:
And then, the second dataset:
Then I merge the two datastores by using 'combine'. However, according to the documentation available here, I should be reading a three-column cell array, wherein the third column would be the labels. I get only two columns when reading though:
If I try to give this combined dataset as input to my network (which has two inputs and one output) I get the following error message:
>> net = trainNetwork(imdsCombined,lgraph_1,options);
Error using trainNetwork (line 170)
Invalid training data for multiple-input network. For a network with 2 inputs and 1 output, the datastore read function must
return an M-by-3 cell array, but it returns an M-by-2 cell array.
I am using R2019b by the way.
So, is there a way to insert the labels column onto the cell arrays read from the image datastore? Or is there something else I need to do?
Thanks for all the help.
Regards,
I would like to retrain the vgg-imagenet-f network to do classification (rather than direct image comparison, which is what I have done with my own network).
The downloaded network however is a deployment net, and doesn't have a loss layer included. As I've not done classification training before, I'm a bit stumped as to how to design this last layer. I expect it will be something like this:
layer.name = 'loss' ;
layer.type = 'custom' ;
layer.forward = #forward ;
layer.backward = #backward ;
layer.class = [] ;
but I don't know what my #forward and #backward functions should be. Should they be softmax?
Of note, I have a imdb with about 10k images, corresponding labels, and an ID element with unique numbers running 1 - 10k.
Thanks for any help, or any links to a sample of the way one should construct this layer in matconvnet/matlab!
You could implement your own network adjusting the filters accordingly, since you want to 'retrain' vgg instead of initializing the weights with random numbers you can adapt your classification network using trained filers from downloaded network. The last layer could be softmaxloss
http://www.vlfeat.org/matconvnet/mfiles/vl_nnsoftmaxloss/
I'm teaching myself classification, I read and understood the MatLab online help of the simple LDA classifier which uses the fisher iris dataset.
I have now moved to SVM. But even though I use the exact syntax from the help page I get an error of either not enough or too many input arguments.
I have made trained my SVMClassifier using svmtrain via the command:
SVMStruct = svmtrain(training,labels);
Where training is a 207 by 900 training matrix. There are 207 samples and 900 HoG descriptors or features. Similarly labels is a 207 by 1 column vector consisting of either +1 or -1 for their respective samples.
I then wanted to test it and see if this works by calling:
Group = svmclassify(SVMStruct,sample,'Showplot',true)
Where sample is a 2 by 900 matrix containing 2 test samples. I was expecting to get +1 and -1 as these are what the test samples should be labelled. But I get the error:
Too many input arguments.
And when I use the command
Group = svmclassify(SVMStruct,sample)
I get the error
Not enough input arguments.
You might have overloaded svmclassify function.
try
>> which svmclassify
to verify that you are actually calling the right function.
In case that you overloaded the function (that is, created a different function with the same name svmclassify) and it is located higher in your path then you'll need to rename the overloaded function and run svmclassify again.
I have a 90×8 dataset that I feature-extracted (by summing 1's in every 10×10 cell) from 90 character images i.e. digits 1-9. Every row represents an image.
I am trying to use following code to train a neural network and recognize new input images(that are digits between 1 and 9 inclusive):
net.trainFcn='traingdx';
net.performFcn='sse';
net.trainParam.goal=0.1;
net.trainParam.show=20;
net.trainParam.epochs=5000;
net.trainParam.mc=0.95;
net =newff(minmax(datasetNormalized'),[20 9],{'logsig' 'logsig'});
T=reshape(repmat([1:9],10,1),1,90);
[net,tr]=train(net,datasetNormalized,T);
Afterwards I want to use the following to recognize new images using the trained network. m is an image character that has also been feature extracted.
[a,m]=max(sim(net,m));
disp(b);
I am getting the following errors and I don't have any idea how to solve it:
Error using trainlm (line 109)
Inputs and targets have different numbers of samples.
Error in network/train (line 106) [net,tr] =
feval(net.trainFcn,net,X,T,Xi,Ai,EW,net.trainParam);
Error in Neural (line 55) [net,tr]=train(net,datasetNormalized,T);
Note: datasetNormalized is my dataset normalized in [0,1].
Which part causes the problem?
Inputs and targets have different numbers of samples. it seems to be the problem
T=reshape(repmat([1:9],10,1),1,90) --> T=reshape(repmat([1:9],10,1),90,1)
[net,tr]=train(net,datasetNormalized,T); --> [net,tr]=train(net,datasetNormalized',T);
T is to be used as target for the network; Therefore, following a friend's advice, I defined T as a 9*90 array in such a way that the first 10 columns have 1 in their first row-other rows being zero, the second 10 columns have 1 in their second row, and so on
T=zeros(9,90);
for j=1:90
i=ceil(j/10);
T(i,j)=1;
end
[net,tr]=train(net,datasetNormalized',T);
This solved the error I was getting upon training network, though I'm not still sure how it's going to be mapped to input characters and determine them.
I am trying to train a simple neural network with Pybrain. After training I want to confirm that the nn is working as intended, so I activate the same data that I used to train it with. However every activation outputs the same result. Am I misunderstanding a basic concept about neural networks or is this by design?
I have tried altering the number of hidden nodes, the hiddenclass type, the bias, the learningrate, the number of training epochs and the momentum to no avail.
This is my code...
from pybrain.tools.shortcuts import buildNetwork
from pybrain.datasets import SupervisedDataSet
from pybrain.supervised.trainers import BackpropTrainer
net = buildNetwork(2, 3, 1)
net.randomize()
ds = SupervisedDataSet(2, 1)
ds.addSample([77, 78], 77)
ds.addSample([78, 76], 76)
ds.addSample([76, 76], 75)
trainer = BackpropTrainer(net, ds)
for epoch in range(0, 1000):
error = trainer.train()
if error < 0.001:
break
print net.activate([77, 78])
print net.activate([78, 76])
print net.activate([76, 76])
This is an example of what the results can be... As you can see the output is the same even though the activation inputs are different.
[ 75.99893007]
[ 75.99893007]
[ 75.99893007]
I had a similar problem, I was able to improve the accuracy (I.E. get different answer for each input) by doing the following.
Normalizing/Standardizing input and output to the neural network
Doing this allows the neural network to more accurately determine the internal weights and values for the network in order to predict the answers
heres an article that explains it in more detail. http://visualstudiomagazine.com/articles/2014/01/01/how-to-standardize-data-for-neural-networks.aspx
In the end I solved this by normalizing the data between 0 and 1 and also training until the error rate hit 0.00001. It takes much longer to train, but I do get accurate results now.