All Questions
Tagged with machine-learning neural-networks
300 questions
11
votes
0
answers
235
views
Tutorial example NetTrain fails miserably with a GPU
I have been experimenting with GPU NetTrain on AWS now when Mma 12.2 supports remote batch jobs (I don't have an Nvidia GPU to try these things out otherwise). In ...
- 19.1k
10
votes
1
answer
480
views
Can we implement a Neural Network interactively?
Implementing a Neural Network manually need some code and need to make some connections between these components.
Can we implementing a Neural Network interactively?If I want to make a net like ...
- 6,866
10
votes
2
answers
427
views
Mathematica 11.1 - Issue with Training Function for Sequence Data
I am attempting to use the new recurrent network functionality in Mathematica 11.1 Home Edition. I created a network that will attempt to predict future bytes in a raw audio file (using very small ...
- 103
10
votes
1
answer
556
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 ...
- 3,830
10
votes
1
answer
372
views
How does mathematica compute loss with multi-losses?
I want to make a DNN that it can learn from text feature(1534-dims) and old audio features(256*4(four old frames)-dims) to predict audio feature(256-dims) at current frame.
So it has two inputs,one ...
- 6,866
10
votes
1
answer
269
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 ...
- 1,535
10
votes
0
answers
786
views
How to train a bounding box detection model?
Apparently, this still isn't possible in v12?
I'd like to add a new class to one of the standard object detection architectures. Consider the YOLO v2 detector from the Neural Net Repo.
...
- 31.8k
9
votes
3
answers
936
views
Example of NetChain running in MXNet cause Error
Cross post here
Problem remains in Mathematica 11.2
First defining the net
...
- 6,866
9
votes
2
answers
327
views
Can I use Mathematica to generate candle scents?
I found this blog (which is highly entertaining). It has an interesting post where the author uses the GPT-2 neuro-network with candle scent training data to generate new candle scents. The AI comes ...
- 4,778
9
votes
1
answer
999
views
How do I implement masked Softmax?
Consider:
input = {1, 2, 3};
mask = {1, 0, 1}
Classic Softmax:
SoftmaxLayer[]@input
{0.0900306, 0.244728, 0.665241}
...
- 9,621
9
votes
1
answer
3k
views
Fashion segmentation with a neural net?
I would like to train a network that can parse clothing:
Does anyone know of a fashion segmentation network with or without pre-trained weights available that I can use in Mathematica?
Update:
I ...
- 31.8k
9
votes
2
answers
400
views
Options for ValidationSet accuracy from NetTrain?
With NetTrain[] if you use the option ValidationSet->Scale[.1] it will run a validation test on 10% of the training data ...
- 31.8k
9
votes
1
answer
268
views
Adding computer vision datasets?
I find having ResourceData/Objects for machine learning datasets to be extremely useful, with their "TrainingData", "TestData" properties:
Right now there's only a handful:
And even fewer for ...
- 31.8k
9
votes
1
answer
152
views
Can Mathematica Neural Net make use of the REC file format for images like MXNet?
When using large set of images for training neural networks (>10000, size 250 x 250 each) the time to read the images is quite long.
My first approach was to use the DataSet functionality of ...
- 131
9
votes
1
answer
311
views
How to implement BlazeFace?
BlazeFace is a lightweight and well-performing face detector tailored for mobile GPU inference. It runs at a speed of 200-1000+ FPS on flagship devices. How to implement BlazeFace in Mathematica?
- 9,621
8
votes
2
answers
853
views
Training data generator?
Python has generators which save memory, is there a technique for generating in memory examples for your training set "on the fly".
For example purposes, I constructed here a regressor for blur:
<...
- 3,830
8
votes
2
answers
703
views
Staged training of Neural Networks
From what the documentation says about NetTrain and NetInitialize and what the progress indicator shows when reevaluating ...
- 8,529
8
votes
1
answer
509
views
Neural net example not working
Bug introduced in 11.0.0 and fixed via paclet update
The Wolfram Mathematica site provides this example.
I have copied and pasted into a notebook. The resource is reached and correctly sampled.
...
- 65.1k
8
votes
1
answer
758
views
Which GPUs does NetTrain work with?
NetTrain's option TargetDevice -> "GPU" works for old macbooks that have GEForce GT 750m cards (like mine), but what about other nvidia cards?
Does it (or will ...
- 3,830
8
votes
1
answer
277
views
Dilation on 3D Images?
I need to apply a dilated convolution to a 3D image, but dilation values greater than 1 are not currently supported in v11.3:
...
- 31.8k
8
votes
1
answer
739
views
NetTrain automatic settings
I'm trying to compare Mathematica's NetTrain with other algorithms, and I used Automatic settings as they were working quite ...
- 999
8
votes
2
answers
946
views
Resources to learn about Neural Nets using Mathematica?
I'm interested in learning about Neural Nets and I'd really like my instruction to be in Mathematica if possible.
For instance, a tutorial like this one: http://neuralnetworksanddeeplearning.com/...
- 570
8
votes
1
answer
656
views
Batching in inference and support for multiple GPUs
I know that Mathematica supports GPU inference, and can be told which GPU to run models on by specifying TargetDevice->{"GPU",2} or such.
My questions are as follows:
1) By using the above statement ...
- 278
8
votes
1
answer
1k
views
Use autoencoder for dimensionality reduction
I have been trying to follow this tutorial (https://www.wolfram.com/language/11/neural-networks/unsupervised-learning-with-autoencoders.html?product=mathematica) to train an autoencoder in Mathematica,...
- 3,167
8
votes
1
answer
5k
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 ...
- 6,866
8
votes
1
answer
209
views
How to extract of sub-net of NetGraph correctly?
net = NetGraph[{3, 5, 8}, {1 -> 2 -> 3}, "Input" -> 2]
Take[net, {1, 2}]
But ...
- 6,866
8
votes
1
answer
215
views
8
votes
1
answer
187
views
Optimize a network topology?
I'd like to know if one can use optimization function like Maximize[] or BayesianMaximize[] to optimize the hyper-parameters of ...
- 3,830
8
votes
1
answer
385
views
Memory leak in NetTrain?
Issue
NetTrain seems to leak memory.
Example
We define a simple NetChain:
...
- 4,694
8
votes
1
answer
724
views
Train your own CycleGAN style translator
I have a set of images (a few hundred) that represent a certain style and I would like to train an unpaired image to image translator with CycleGAN.
I'm looking for a tutorial on how one would do ...
- 3,830
8
votes
0
answers
156
views
Slow down training many neural networks (Bug?)
I am working on something in which I need to train a neural network many times with slightly different training data. I noticed that after many training runs the input rate had dropped significantly.
...
- 363
8
votes
0
answers
433
views
Use of new machine learning capability for search problems (reinforcement learning)
I work with search algorithms, often of an adversarial nature, and want to understand how to apply Mathematica's machine learning capabilities, especially those new in version 11, to this type of ...
- 4,102
7
votes
3
answers
888
views
how to take ImageFeatures?
I want to know how to transform images to feature vector.
There is a function FeatureExtractor.And it has some methods.
...
- 449
7
votes
1
answer
436
views
Implementing Resnet as a NetGraph?
Does anyone know of a Mathematica v11.1 implementation for any of the Resnets, e.g. a NetModel or WLNet for Resnet-1000?
Loading the MXNet weights from the model zoo for both resnet or resnext doesn'...
- 31.8k
7
votes
1
answer
195
views
7
votes
1
answer
325
views
NetPortGradient output port restriction
The documentation for NetPortGradient says
net[<|..., NetPortGradient[oport] -> ograd|>, NetPortGradient[iport]] can ...
- 1,244
7
votes
1
answer
127
views
How to calculate a PDF of a neural network output?
I have to find the probability density function of the output of an internal layer in a neural network.
I wanted to do it using NetMeasurements adding a layer like
<...
- 215
7
votes
1
answer
178
views
Running Mathematica in 'SpouseMode'
In this previous question I looked into a deprecated capability of Mathematica from Version 2.
Mathematica command that allows it to read my intentions
Thanks to all for your answers. I note that ...
- 7,213
7
votes
0
answers
159
views
How to extend ImageCases?
I was very excited to see ImageCases being documented in version 12. But I immediately desired a mechanism for adding more entities to ...
- 31.8k
7
votes
1
answer
772
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). ...
6
votes
1
answer
1k
views
Save neural network after training
I've written quite a few projects that involve training a neural network through the Classify and Predict functions, but every ...
- 539
6
votes
1
answer
539
views
Extract neural network model from ClassifierFunction
I'm very new to Neural Networks and Mathematica 11 (I used MMA8 some time ago) and I'm trying to learn about NN using Mathematica. I'm using MMA 11.2 in a Rapsberry Pi (yes, I know that doing NN in a ...
- 253
6
votes
1
answer
2k
views
How to make a switch in Neural Networks?
In this paper,they design a network like this.
The left(green) is a normal network that mapping one feature to another feature,the right(red) side is an autoencoder(using RNN).But a switch is ...
- 6,866
6
votes
1
answer
1k
views
Is it possible to fix the weight of a certain layer during neural network training?
As suggested by the title, is it possible to fix some part of the neural network while training?
Since Mathematica provides a way to extract part of a neural network and combine it with some layers ...
- 269
6
votes
2
answers
4k
views
Neural network: Line detection in Image
I am playing around with Mathematica's new Neural Network toolbox and am trying to teach a network to detect lines in quite noisy images.
An example Input image would look like the following:
The ...
- 1,535
6
votes
1
answer
1k
views
How do I create & train a neural net to predict a stock closing price at T+5min using OHLC and other data?
I'm trying to create a neural network and train it to test predictability of short term stock price movements.
I've collated a 1-min open, high, low, closing and volume dataset for a particular stock....
6
votes
1
answer
221
views
Is it possible to convert the result of NetTrain to a PredictorFunction?
I would like to use PredictorMeasurements on the result of NetTrain, but it says it expects a ...
6
votes
1
answer
188
views
Unexpected high memory consumption using out-of-core NetTrain
I'm working on training a neural network on an image dataset. There are 14k images and each image contains 3x150x150 pixels. I have built a generator function following the approach in Training on ...
- 544
6
votes
1
answer
218
views
Compute neural network loss over sliding windows?
I am trying to use the structural similarity index, which is defined in terms of a computation over sliding windows, as a neural network loss function.
Obviously one can get a sliding mean using a <...
- 1,138
6
votes
1
answer
283
views