I am new to Torch.
I am trying to run single classifier Experiment in Torch.But,I am getting the following error when Training is started,
/torch/install/bin/luajit: bad argument #2 to '?' (out of range at /torch/pkg/torch/generic/Tensor.c:853)
stack traceback:
[C]: at 0x7f17b9dc029
[C]: in function '__index'
.../torch/install/share/lua/5.1/optim/ConfusionMatrix.lua:40: in function '_add'
.../torch/install/share/lua/5.1/optim/ConfusionMatrix.lua:102: in function 'batchAdd'
Main.lua:246: in function 'Train'
Main.lua:289: in main chunk
[C]: in function 'dofile'
.../torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:131: in main chunk
[C]: at 0x00406670
Is it possible to train single classifier network in Torch?
Thanks in advance.
Thanks for your reply.
My model contains,
classifier = nn.Sequential()
classifier:add(nn.Dropout(0.5))
classifier:add(nn.Linear(512,512))
classifier:add(nn.BatchNormalization(512))
classifier:add(nn.ReLU(true))
classifier:add(nn.Dropout(0.5))
classifier:add(nn.Linear(512,1))
classifier:add(nn.LogSoftMax())
and I am using nn.CrossEntropyCriterion() for Loss in the network.
Is it possible to run single classifier experiment?
Yes, you can train in one class.
The error you got is pointing towards confusion matrix.
For one class it should be in the following way:
-- classes
classes = {1}
-- This matrix records the current confusion across classes
confusion = optim.ConfusionMatrix(classes)
Your train labels or test labels should never contain '0' number as the label.
Related
I'm familiarizing myself with Pyspark and SparkML at the moment. To do so I use the titanic dataset to train a GLM for predicting the 'Fare' in that dataset.
I'm following closely the Spark documentation. I do get a working model (which I call glm_fare) but when I try to assess the trained model using summary I get the following error message:
RuntimeError: No training summary available for this GeneralizedLinearRegressionModel
Why is this?
The code for training was as such:
glm_fare = GeneralizedLinearRegression(
labelCol="Fare",
featuresCol="features",
predictionCol='prediction',
family='gamma',
link='log',
weightCol='wght',
maxIter=20
)
glm_fit = glm_fare.fit(training_df)
glm_fit.summary
Just in case someone comes across this question, I ran into this problem as well and it seems that this error occurs when the Hessian matrix is not invertible. This matrix is used in the maximization of the likelihood for estimating the coefficients.
The matrix is not invertible if one of the eigenvalues is 0, which occurs when there is multicollinearity in your variables. This means that one of the variables can be predicted with a linear combination of the other variables. Consequently, the effect of each of the variables cannot be identified with any significance.
A possible solution would be to find the variables that are (multi)collinear and remove one of them from the regression. Note however that multicollinearity is only a problem if you want to interpret the coefficients and not when the model is used for prediction.
It is documented possibly there could be no summary available for a model in GeneralizedLinearRegressionModel docs.
However you can do an initial check to avoid the error:
glm_fit.hasSummary() which is a public boolean method.
Using it as
if glm_fit.hasSummary():
print(glm_fit.summary)
Here is a direct like to the Pyspark source code
and the GeneralizedLinearRegressionTrainingSummary class source code and where the error is thrown
Make sure your input variables for one hot encoder starts from 0.
One error I made that caused summary not created is, I put quarter(1,2,3,4) directly to one hot encoder, and get a vector of length 4, and one column is 0. I converted quarter to 0,1,2,3 and problem solved.
I'm using the Caffe library for training a convolutional neural network (CNN). However, I'm getting the following error when using the concat layer to combine the output from two convolutional layers before applying it to a inner_product layer.
F1023 15:14:03.867435 2660 net.cpp:788] Check failed: target_blobs[j]->shape() == source_blob->shape() Cannot share param 0 weights from layer 'fc1'; shape mismatch. Source param shape is 400 800 (320000); target param shape is 400 400 (160000)
As far as I know I am using the concat layer in the exact same way as in BVLC_GoogLeNet. The concat layer can be found in my train.prototxt at pastebin under the name combined. The dimensions of my input blob is 256x8x7x24, where the data format in Caffe is batch_size x channels x height x width. I've tried training both using the pycaffe interface and the console. I get the same error. Below is code for training using the console.
solver_path = CAFFE_ROOT+'build/tools/caffe train -solver '
model_path = self.run_dir+'models/solver.prototxt'
log_path = self.run_dir+'models/training.log'
p = subprocess.Popen("GLOG_logtostderr=1 {} {} 2> {}".format(solver_path, model_path, log_path), shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
What is the meaning of this error? And how can it be resolved?
Update
As mentioned in the comments the log contains nothing else than the error. The stack trace for the error is the following:
# 0x7f231886e267 caffe::Net<>::ShareTrainedLayersWith()
# 0x7f231885c338 caffe::Solver<>::Test()
# 0x7f231885cc3e caffe::Solver<>::TestAll()
# 0x7f231885cd79 caffe::Solver<>::Step()
# 0x7f231885d6c5 caffe::Solver<>::Solve()
# 0x408d2b train()
# 0x4066f1 main
It should also be noted that my solver and code works fine for training the exact same CNN with only 1 "path" along the network, i.e. without the CONCAT layer.
I believe the issue you're having is that your train net has been updated to have a concat layer while your test net hasn't.
It would explain the 400x400 vs 400x800 issue you're having considering your concat merges two 400x400 layers. I can't know for certain without being able to see your test net.
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'm doing some cross-validation using a Matlab Weka Interface that I got from file exchange. My loop structure seems to work fine for Weka's Logistic classifier. However, when I try to do the exact same thing for AdaBoostM1, it throws the following error:
??? Java exception occurred: java.lang.ArrayIndexOutOfBoundsException
Error in ==> wekaClassify at 24 classProbs(t+1,:) = (classifier.distributionForInstance(testData.instance(t)))';
Error in ==> classifier_search at 225 [pred ~] = wekaClassify(matlab2weka('instance', featurelabels, tester), classifier);
I have determined through some testing that this only occurs when the number of instances in the training set is greater than the number of instances in the test set. I am sure you can see why that is a problem for me, since in most situations the training set is greater than the test set in size.
Is there something different about how I should format my inputs when using Adaboost rather than Logistic? Any information you can give regarding this problem would be so helpful.
I downloaded this code from this page: http://www.mathworks.com/matlabcentral/fileexchange/21204-matlab-weka-interface
Emails bounce from the account of the guy who made it, and he doesn't seem to respond to comments on the page - I'm hoping that maybe someone here has used this.
EDIT: Here is the code that I use to train and test the classifier:
classifier = trainWekaClassifier(matlab2weka('training', featurelabels, train), 'meta.AdaBoostM1', { strcat('-P 100 -S 1 -I ', num2str(r), '-W weka.classifiers.trees.DecisionStump')});
[pred ~] = wekaClassify(matlab2weka('instance', featurelabels, tester), classifier);
I haven't used this combination of software, so I can only take a guess at what could cause this.
Are your training/testing data matrices the right way round? They should be N-by-D (N instances, D features).
If you were passing in a D-by-N training matrix and a D-by-M testing matrix, then I would expect it to work only when M < N - which is what you describe - and even then, it wouldn't give a meaningful result.
I am very new in Matlab and that too in Neural network.. I have 4*81 input dataset and 1*81 output/target dataset. 'divideblock' or 'dividerand' randomly split the dataset into training, validation and testing.My question is that... After training and simulation... how to trace the individual input dataset(training, testing, validation) which are used to train the network.
so that i can able to find the error of the input dataset for testing, validation individually..
thanks in advance for any suggestion...
Use trainInd,valInd,testInd:
[trainInd,valInd,testInd] = dividerand(Q,trainRatio,valRatio,testRatio);
see http://www.mathworks.com/help/toolbox/nnet/ref/dividerand.html .