Questions tagged [machine-learning]

Questions about machine learning functionality of Mathematica, for instance involving, but not restricted to, Predict, Classify, FindClusters and the various regression functions.

Filter by
Sorted by
Tagged with
3
votes
1answer
178 views

Tutorial on net surgery?

I'm trying to replace the "fc1000" layer in a NetModel, what am I missing here: ...
3
votes
1answer
149 views

How exactly does NetTrain use a ValidationSet (can we reuse it as TestSet)?

Typically when you train a model you have three sets of data: training, validation, and testing - and they can’t be mixed, i.e. you can’t use images from one in the other. I want to know if the ...
14
votes
0answers
524 views

How to plug holes in an Image (with partial convolutions)?

NVIDIA recently published a new way to reconstruct images with holes. They use a new type of convolutional layer which is described in the paper Image Inpainting for Irregular Holes Using Partial ...
9
votes
1answer
257 views

NetEncoder for images of “Varying” dimension?

I'm looking for someway to do what this syntax "should" do: NetEncoder[{"Image", Automatic, ColorSpace -> "RGB"}] /@ imgs; The documentation states that ...
3
votes
1answer
76 views

Validation failed for ConvolutionLayer message?

I have a simple fully convolutional network and I'm trying to figure out why I get this error NetChain::valfail: Validation failed for ConvolutionLayer: kernel size 3*3 plus padding size 0*0 cannot ...
6
votes
1answer
355 views

FindFaces in Mathematica 11.3

I just upgraded to Mathematica 11.3. but now my FindFaces instructions do not work anymore. I guess they changed the syntax in 11.3. Here is the original code: <...
4
votes
1answer
150 views

how to use CatenateLayer to connect nodes within a NetChain

EDIT: Looking closely at my network I have a similar problem of providing inputs to the CropLayer function. The output from the pooling layer (node 30) and node 87 (activation) should feed to the ...
3
votes
1answer
40 views

How to replace all activations in a NetGraph?

I'm trying to replace all activation layers of a certain type, there must be a simpler way to do this? ...
2
votes
0answers
62 views

Unable to create ClassifierMeasurements for NetGraph

I am trying to check the accuracy of a neural network by using ClassifierMeasurements. I take the MNIST as example:- Code for setting ...
2
votes
1answer
66 views

Unable to create NetGraph

I am trying to perform deep learning classification in Mathematica. I noted that I am unable to create NetGraph even when I just follow the simple steps in the help ...
2
votes
1answer
113 views

Specify NetEncode's tokenization model?

NetEncoder[{"Tokens"}] uses WordData indices to tokenize an input string. But is there a way to tell ...
1
vote
0answers
71 views

BayesianMinimization not giving the optimal values

I was following the examples given in the BayesianMinimization documentation and I found that this function actually does not give me the minimal value (very close though). Can anyone help explain the ...
4
votes
2answers
202 views

NetTrain with multi-label data?

I'm attempting to do simple category recommendation on textual data. I have around 20k training samples of the form desc_String -> {tag1_String, tag2_String, ...}...
3
votes
0answers
203 views

Is is a bug when importing MXNet model?

There is a trained net:model.zip Using Python to make prediction: ...
2
votes
1answer
132 views

Plotting a precision recall curve?

I would like to plot some PR curves for a few different applications: results on a test set for a (multilabel multiclass) classifier results on a test set for a CBIR function that returns ranked ...
0
votes
1answer
193 views

How do I change activation function of LinearLayer[] in NetGraph

I want to analize a network such that all neurons of its hidden layers output LogisticSigmoid[w.x+b], which is one of the most common ouputs analized in a neuron. ...
4
votes
1answer
141 views

Single Neuron Dream Example (from Markus van Almsick's Presentation WTC 2017)

I'm teaching myself about Mathematica 11.3 Neural Net capabilities, and I can't get a demonstrably previously working example to work. I've been trying for quite a while without success. In Martin ...
5
votes
1answer
192 views

Custom Loss Layer to ignore ordering

I am trying to train a net that takes a sequence of numbers and gives a sequence of numbers. For example: ...
10
votes
1answer
234 views

Can one use NetTrain with two Nvidia GPUs?

I am thinking of buying another GPU to accelerate my training. Will I be able to call NetTrain with both GPUs ("TargetDevice"-> {"GPU", All})? Or would it be ...
3
votes
0answers
164 views

Image Segmentation: (Efficient Graph-Based)

This question is two-fold; First, it is about how to get the speed efficiency this algorithm should provide in Mathematica. In addition, it has a small question about the algorithm (Efficient Graph-...
1
vote
1answer
157 views

Using NetTrain with HDF5?

I have some nicely formatted training data in HDF5 files, i.e. the images and labels are serialized within the H5 file as groups and datasets. AFAIK NetTrain only ...
4
votes
1answer
69 views

How to restore trained classifier/predictor from persistent storage?

Mathematica 11.3 has the ability to store trained classifier/predictor in the notebook. But how can we restore it in the new session? Create notebook and measure it's size: ...
0
votes
0answers
54 views

Whats the best way to classify data for Fall detector device?

I would like to know what's the best way or the function to use to classify 2 files for a fall detection device. my first file contains only TDL (Normal Movements) values and the second contains only (...
8
votes
1answer
161 views

How to use a remote windows laptop for NetTrain?

I have a windows 10 laptop (with a gpu) at home and a macbook at my office, both with v11.3. What are steps to use the windows machine remotely for training? That is, I want to launch and run ...
2
votes
1answer
118 views

Error using accuracy and ConfusionMatrixPlot of ClassifierMeasurements

EDIT: Here is the complete code that i have used: ...
5
votes
1answer
354 views

Image Generator with a Neural Network (CIFAR-10)

As some of you may know, CIFAR-10 is a data base which has 60,000 images (which are 32x32 in size) of 10 different categories (airplane, dog, cat, frog, deer, bird, horse, ship, automobile and truck). ...
2
votes
2answers
151 views

ElementwiseLayer with Piecewise?

I need a specific custom activation function; how can I implement it with Piecewise? This is what I've tried (using the recommendation from this question): ...
3
votes
1answer
96 views

Using NetGraph as FeatureExtractor?

I'd like to compute FeatureDistance between two images with a NetGraph: rs = NetModel["ResNet-152 Trained on ImageNet Competition Data"]; fe = NetTake[rs, {1, -3}] ...
19
votes
0answers
183 views

Inefficient memory storage for Dataset

Why Dataset doesn't serialize its contents, isn't it the whole point? I expect it to behave similar to python's pandas.DataFrame,...
3
votes
0answers
102 views

How to perform unsupervised texture classification?

Consider a texture mixture (img) from Brodatz. I want to classify the five different texture patterns and segment the corresponding regions. Following this, I ...
13
votes
2answers
638 views

How to implement a triplet network with NetSharedArray?

In v11.3, NetSharedArray[] and NetInsertSharedArray[] give us a mechanism of sharing weights and biases across neural networks, ...
2
votes
1answer
62 views

How does DimensionReduce work for EventData?

My question is whether the use of DimensionReduce, for a simple example with Method -> "PrincipalComponentsAnalysis" is the ...
4
votes
0answers
414 views

Using Machine Learning techniques for text-analysis

I am analysing a bunch of tweets and I want to understand which political party the authors support. Let say, for example that I have five parties labelled by a number: ...
0
votes
0answers
75 views

Training speed of NetTrain on GPU

I have a model with NetTrain that works fine. However, as I increase the amount of training data, the number of inputs per second to my GPU drops very, very substantially. In fact, when I include all ...
4
votes
0answers
49 views

NetTrain doesn't accept sparse input?

The following code fails to execute: ...
0
votes
0answers
68 views

Neural Network and Enforce Positive Vector

I am trying to implement a neural network where I output a vector of 5 parameters each of which I know to be positive. I have code that works where I end up with an `"Output" -> 5.' However, after ...
0
votes
0answers
123 views

Change Loss Function in NetTrain

For a similar problem, I am trying to modify the code here (https://www.wolfram.com/language/11/image-and-signal-processing/image-recognition-using-deep-learning.html?product=mathematica) so that the ...
2
votes
0answers
87 views

Significant performance differences with “Predict” function between v10 and v11

So I am very new to ML. I tried running this code in Mathematica 10.4.1.0 ...
3
votes
1answer
214 views

What is Mathematica's ML Linear Regression Method?

When I run p = Predict[trainingSet, Method -> "LinearRegression"];, how is that different from just running ordinary least squares? It's quite slow on a ...
6
votes
0answers
284 views

How “good” is the new Classify and how does it choose its method

I recently read the blog regarding data-science Wolfram Blog and then checked the quality of the new Classify. I have a bunch of slides that I show to my students ...
2
votes
0answers
83 views

Specifying feature types for BayesianMinimization

I'd like to use Bayesian optimization over a pair of features, one nominal, one numerical. If I do something like this: ...
5
votes
0answers
125 views

What's BayesianMinimization and related functions based on?

Is it specified anywhere what the backend is for the Bayesian optimization related functionality in Mathematica v11? I'm specifically referring to the Bayesian* ...
2
votes
0answers
78 views

Apply a classifier to a column in excel and export side by side result? [closed]

I'm relatively new to using Mathematica, and I was able to create a Classifier from a training set of about 3,000 pairs of non-numerical text strings. I have my test set of about 20,000 records in an ...
3
votes
0answers
70 views

FeatureSpacePlot freaks out with LatentSemanticAnalysis on words

I'm playing with FeatureSpacePlot on a collection of words: ...
2
votes
1answer
167 views

Can Predict return non-numerical values?

I just started working with the Mathematica machine learning package. When I use Predict, I can predict only numerical values like ...
1
vote
0answers
151 views

Machine Learning Predict Precision

I have this code p = Predict[{1 -> 123456789123456789, 3 -> 987654321987654321}] values are big, more than 15 digits (standard machine precision). when I ...
2
votes
0answers
85 views

ClusterClassify and FeatureTypes

I have a dataset that I want to classify in clusters. All values are numbers. For some variables, the values can represent a real measure (a distance, a weight...) but for some other variables, the ...
6
votes
1answer
4k views

How to train Sequence-to-sequence autoencoder using LSTM?

According Keras blog,I find the Seq2Seq auto-encoder. But it didn't give any example only code. To build a LSTM-based autoencoder, first use a LSTM encoder to turn your input sequences into a ...
3
votes
1answer
306 views

Machine learning classify function with audio and set of pictures

As I see from documentation, Classify function supports Audio and Pictures as input, video is not supported unfortunately :( Will it work if I try to use classify for mixed data input like ...
3
votes
0answers
230 views

1
3 4
5
6 7
11