Questions tagged [neural-networks]

Questions involving defining, training, executing, importing and exporting neural networks.

Filter by
Sorted by
Tagged with
1
vote
1answer
89 views

Neural network not training due to function not loading

I'm trying to train a neural network on Mathematica 11.3, but NetTrain won't work and gives the follwoing error: ...
11
votes
1answer
450 views

Creating an indicator function in a neural network

I am working on implementing the loss function of the Yolo version 2 object detection network and building from the construction notebook in the Wolfram Neural Network repository Yolo Version 2 so I ...
0
votes
0answers
40 views

how to train a neural network [duplicate]

I have developed the following code, but I would like to train a neural network so that it can recognize all the dog breeds, integrating many images in order to have a high probability that the ...
2
votes
1answer
75 views

Issue deploying a FormPage using Classify

I developed this code that allows me to recognize what breed is the dog in the inserted image (for the time being developed only for five breeds of dogs), however, when I go to insert the image in ...
6
votes
1answer
211 views

Symbolic Neural Networks in Mathematica

Mathematica is very well known about its symbolic capabilities/functionality. Heavy users usually say that “everything is a symbolic expression”. Does this principle apply to neural networks? If not, ...
2
votes
0answers
31 views

Graphic scaling of neural network SummaryGraphics

Same funky scaling occurs when dragging the SummaryGraphics with the mouse; so, the issue is in the graphics itself not in the ...
1
vote
0answers
63 views

Monitoring the Training Progress through PutAppend

I would like to export the round loss during my model training for each training round. Currently, I am using the way shown in the Documentation Center around TrainingProgressFunction and PutAppend: <...
10
votes
2answers
126 views

Controlling the randomness of DropoutLayer

How can I control the randomness of DropoutLayer in order to get the same result after each execution? For example: ...
3
votes
1answer
136 views

Identify emotions from a drawn face using machine learning?

Can someone tell me how you could modify this code so that it recognizes more facial expressions? ... thanks for the help. ...
1
vote
1answer
106 views

What do the numerical values obtained from “FeatureExtraction” mean and what are their applications?

I started a self study on machine learning with mathematica recently. I have seen the power of predict and classify. I am particularly impressed with "FeatureExtraction" function but I really want to ...
0
votes
0answers
49 views

NetTrain doesn't properly train classifier network

I'm using NetTrain to make a simple classifier network that takes integers 0-9 as inputs and classifies them into ten classes labeled by integers 0-9 as well. My training data maps the inputs to the ...
2
votes
0answers
165 views

Neural Network Time Series Input

All, I am attempting to replicate the work done using Long Short Term Momory Artificial Neural Networks proposed in this thesis by following this (great) example. I have a given dataset for which I ...
0
votes
0answers
29 views

Applying Arbitrary Size Feature Sets to NetTrain

The attached code, worked out at the 2018 Summer Camp, reads a list of training examples, in this cases 93 examples each a list of five features, runs them through NetTrain, then gets back the five ...
3
votes
3answers
108 views

Why Graph does not recognize chains of vertexes like NetGraph

Cross posted on Wolfram Community. Perfect logic: NetGraph[{1, 1, 1}, {1 -> 2 -> 3}] But this does not make sense: ...
4
votes
0answers
61 views

Candidate sampling for softmax neural networks in mathematica

Though I've been using mathematica for a few years, I've never really delved into its ML capabilities (except for the occasional clustering). I'm curious if anyone who has some experience using ...
1
vote
1answer
86 views

Problem of result of TopProbabilities in NetModel

Bug introduced in 11.3 and fixed in 12.0.0 I'm on Mathematica 11.3, Classify model could use TopProbabilities without designating an integer. ...
7
votes
1answer
168 views

NetPortGradient output port restriction

The documentation for NetPortGradient says net[<|..., NetPortGradient[oport] -> ograd|>, NetPortGradient[iport]] can ...
3
votes
0answers
124 views

Backpropagation for manual neural network training [duplicate]

I need to train a neural network manually. Is there a simple way to get the derivatives of all of the learned parameters in the network (with respect to the output) via backpropagation, other than ...
1
vote
0answers
88 views

How to use UnitVectorLayer in a NetChain?

How can I create a NetChain with UnitVectorLayer inside? In this way I receive this error: ...
1
vote
0answers
116 views

Next element of the list prediction

I want to make a prediction which element will be next in the list. To make an example, on a certain date certain number appears, so I have a list of {date, number} elements. I wanted to use Predict ...
3
votes
1answer
105 views

Why does this NetTrain example fail?

I have some training data of the form {{x, y}, bool}, e.g. ...
-1
votes
1answer
192 views

how to import mathematica trained mxnet neural net

How to import mathematica trained mxnet neural net into python and use it there? Can someone provide a simple example i can use as a template. Thanks
4
votes
0answers
104 views

How to do broadcast in NeuralNetworks?

In normal case, we can multiply the tensor by the scalar, vector like this: ...
3
votes
1answer
89 views

Custom “Function” NetDecoder

I was surprised to learn that there is no custom "Function" named decoder for NetDecoder, as there is for NetEncoder. Has anyone ...
4
votes
2answers
220 views

Why doesn't NetTrain use GPU as TargetDevice?

I have a NetTrain call with the following parameters: tNet = NetTrain[inVecs -> outVecs, TargetDevice -> "GPU"]; But ...
12
votes
3answers
358 views

Convert List of Associations into Association of Lists

For neural networks mathematica likes 2 ways to structure training sets: ...
7
votes
1answer
713 views

How to perform noisy circle detection

I want to detect circles that are embedded in noise. For this I created a few circles with some defined signal-to-noise ratio: ...
3
votes
1answer
147 views

How to use FastText embeddings in a NetGraph?

Does Mathematica 11 have access with either the Wikipedia or CommonCrawl FastText embeddings? Maybe this is built-in through the Neural Net Repository or available through a ...
11
votes
1answer
326 views

Quantile Regression using Neural Networks (Custom Loss function)

I would like to perform a Quantile Regression within Mathematica's neural network framework. Since there exist a couple of tutorials for this exact problem in Tensorflow, i.e. Deep Quantile ...
4
votes
0answers
97 views

Capsule Network reconstruction layer

I am experimenting the capsule network, using the architecture provided here: Capsule Network in Mathematica Deep Neural Network Repository While I can figure out what the network do following the ...
3
votes
0answers
84 views

How to access coefficients and gradients of neural networks?

I would like to test optimization for neural networks for that I need to access the weights/bias of the different layers and the derivatives of the output or a loss function with respect to these ...
3
votes
1answer
42 views

How does NetDecoder for Tokens work?

I'm trying to understand why I can decode encoded word tokens? ...
10
votes
1answer
380 views

NetTrain an image caption generator

I would like to write out the simplest possible word-by-word image caption generator. This network should take an image and build a sentence describing it. Here is my fashion dataset of images and ...
4
votes
1answer
94 views

How to use NetBidirectionalOperator?

I'm a little uncertain as how to use NetBidirectionalOperator. In other frameworks, switching an LSTM to be bidirectional is an option but you have to double the ...
3
votes
0answers
92 views

NetModel fails to load a pre-trained model: Very Deep Net for Super-Resolution, in 11.3

I'm trying to run VDSR in Mathematica 11.3 on windows. My situation is: in: NetModel["Very Deep Net for Super-Resolution"] out: ...
3
votes
0answers
112 views

Can you train ImageClassify model with multiple GPUs correctly?

After some testing, I still cann't train with two GPU in Windows 10. But I can train with Mathematica 11.3 in Ubuntu 16.04 with two graphics card GTX 1080 The problem is, If I use two card to train, ...
6
votes
2answers
117 views

How does “BeamSearch” work?

I'd like to see a more intuitive example of what this type of net decoder actually does (in the context of lstm's and text/caption generation). This is the only example in the docs: and I have no ...
6
votes
1answer
101 views

Using LearningRateMultipliers in a recurrent neural network

I'm trying to use LearningRateMultipliers in a recurrent neural network, but I haven't found the right way yet. An example of the code is as follows: ...
6
votes
1answer
77 views

Neural network with adaptive color channel

If we have a grayscale network ("Input" -> {1, Automatic, Automatic}), it can be applied on both gray and color image by: ...
12
votes
2answers
473 views

How to define a PixelShuffle Layer?

PixelShuffleLayer come from Real-Time_Single_Image. Firstly, a $C\times H\times W$ image, after a convolution, now $f^2\cdot C \times H\times W$, then sub-pix, finally get a $ C \times fH\times fW$ ...
15
votes
1answer
427 views

Training Neural Networks on Cloud GPUs (Wolfram Cloud / AWS / Paperspace /etc)

I have spent a lot of time lately training neural networks. However, my poor laptop has only an AMD GPU, so I am stuck training these networks on the CPU. That means I get to train networks over ...
0
votes
0answers
82 views

Basic Feed Forward Network

I am trying to build a simple neural network, with an input layer of 250 nodes, 2 'hidden' layers each of 100 nodes, and an output layer with 1 node. I want each node to take in the linear ...
3
votes
1answer
142 views

How to modify NetTrain's error calculation

I'm training a neural network at the moment on an image segmentation problem (that is, I have an images and masks, and I am trying to train the network to generate its own masks from other images. I'...
3
votes
1answer
82 views

How to build a Neural Network with only categorical variables?

I've built mixed data NN, but I'm trying to build an NN that only has categorical variables. In my problem, I cannot represent my categorical variables using the commonly used ...
3
votes
1answer
99 views

How to reconstruct the result of FeatureExtraction?

For the below code for Mathematica 11.3, I got {-0.153792, 1., 1.} as output. ...
0
votes
1answer
89 views

Problem of Low Accuracy of NeuralNetwork Method in Classify MNIST 11.3

The accuracy is extremely low... even after changing a lot of options of Method... Other methods' result is fine and normal, 0.80 accuracy like LogisticRegression. ...
4
votes
1answer
132 views

Value for output of layer is inconsistent (implementing SqueezeUNET from Keras)

I'm attempting to implement this neural network in WL: https://github.com/lhelontra/squeeze-unet/blob/master/squeezeunet.py which is a variant of the SqueezeNet network that does image segmentation. ...
2
votes
0answers
78 views

Why is the output of the Embedding layer so non-linear?

I have 2 nets, i.e. net1 (i.e. LinearLayer) and net2 (i.e. ...
2
votes
1answer
86 views

Custom NetEncoder

I've been trying to train an RNN on some data that I pre-processed externally and saved to disk. My dataset is too large to fit in memory and is additionally varying in shape. Looking for a way to do ...
5
votes
1answer
97 views

Why would a symmetric image have an asymmetric PoolingLayer-Gradient Image?

I have a symmetric image img. For simplicity, I would use the below image as my example: ...