All Questions
Tagged with machine-learning neural-networks
62 questions
73
votes
6
answers
5k
views
Q&A Mathematica v.11 Neural Networks: A comprehensive look at Layers, Net Functions, and pioneering into this [[experimental]] code
Motivation
As Mathematica v.11 was released earlier this month with a host of new [[experimental]] functions and a limited number of examples on curated data that ...
- 5,442
48
votes
2
answers
9k
views
Object detection and localization using neural network
Four important computer vision tasks are classification, localization, object detection and instance segmentation (image taken from cs224d course):
These four tasks are all built on top of the deep ...
- 27.8k
20
votes
4
answers
1k
views
How to use Mathematica to train a network Using out of core classification?
I see there is doc about how to train a network Using out of core image classification and this question.But the object is only image.
I want to use a binary file as data(Sequence to Sequence case),...
- 6,866
20
votes
2
answers
1k
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 ...
- 13.2k
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
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
48
votes
5
answers
4k
views
Generative Adversarial Network
Generative adversarial networks (GAN) is regarded as one of "the most interesting idea in the last ten years in machine learning" by Yann LeCun. It can be used to generate photo-realistic images that ...
- 27.8k
12
votes
1
answer
1k
views
Configuring GPU for NetTrain
I currently have access to a system with two GPUs:
GeForce GTX 1080 and Tesla K40c
I would like to use this machine for training neural networks in Mathematica.
When using the option ...
- 1,410
11
votes
1
answer
406
views
How to view ClassifierFunction's preprocessed data?
Classify apparently preprocesses your input data, for example (same example from Classify reference page, but using ...
- 360
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
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 ...
- 3,820
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:
<...
- 3,820
91
votes
1
answer
14k
views
Crack CAPTCHA using deep learning
Deep convolutional neural networks are very good at computer vision related tasks. Optical Character Recognition (OCR) is one important branch of computer vision. In fact, the convolution neural ...
- 27.8k
48
votes
3
answers
3k
views
Generalized Backpropagation for Neural Networks (e.g. DeepDream)
Is there currently any way to abuse NetTrain to maximize an arbitrary cost/utility -function in some hidden layer and/or even modify the input to increase neuron ...
- 8,529
36
votes
1
answer
3k
views
RNN in Mathematica?
Recurrent neural network is an important part of machine learning and its improved version: LSTM network is widely applied, but Mathematica seemingly is in lack of these two features and in my opinion,...
- 9,660
28
votes
1
answer
2k
views
How to export an MXNet?
I was hoping there was some way to generate the .params and .json file needed to define an MXNet model, from a network trained using NetTrain[] in Mathematica. I ...
- 3,820
17
votes
1
answer
1k
views
How to implement a stateful RNN?
If the model is stateless, the cell states are reset at each example. With the stateful model, all the states are propagated to the next example. Stateful RNNs can learn the long sequences.
For ...
- 9,621
16
votes
1
answer
2k
views
How to visualize attention?
In the articles about sequence attention we can see images like this:
Here we see that while translating from French to English, the network attends sequentially to each input state, but sometimes it ...
- 9,621
15
votes
1
answer
509
views
Using PredictorMeasurements with a neural net?
PredictorMeasurements doesn't work with NetGraph, here's an example:
...
- 3,820
13
votes
2
answers
2k
views
How to change NeuralNetwork options?
How can I manipulate the architecture and problems of a NeuralNetwork in Predict or Classify? For example, running the following ...
- 968
12
votes
3
answers
775
views
How to make Advanced Activations Layers in Mathematica?
I want to try Advanced Activations Layers in Mathematica,but not found.
So I try to use ElementwiseLayer to implement it.
...
- 6,866
7
votes
1
answer
325
views
NetPortGradient output port restriction
The documentation for NetPortGradient says
net[<|..., NetPortGradient[oport] -> ograd|>, NetPortGradient[iport]] can ...
- 1,244
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
58
votes
5
answers
8k
views
Mathematica command that allows it to read my intentions
In version 2.0 of Mathematica there was a command, ReadProgrammerIntentions[ ] which allowed it rapidly compose code that could solve problems simple to complex, ...
40
votes
2
answers
2k
views
How can I export my learned ClassiferFunction[] and PredictorFunction[]s?
Mathematica 10 provides beautiful high-level machine learning functionality. Sadly, the learned functions once created are rather opaque objects. I need to use them in other projects, so here is my ...
- 3,820
35
votes
4
answers
1k
views
How to make a custom NN layer in Mathematica?
Is there a way to create our own custom layers for Neural Networks in Mathematica ? I suspect it should be possible, any pointers or directions on how to go about it?
I am interested in ...
- 401
23
votes
1
answer
943
views
How to ImageRestyle high-res images?
I’m running v12 now and ImageRestyle[] crashes for me on an image of size 1600 x 1200 pixels.
All the examples in the documentation use images around 500 x 500 or ...
- 31.8k
22
votes
5
answers
4k
views
Recurrent neural network in 11.1 explicit examples?
I heard that RNN was implemented in Mathematica as of 11.1. Trying to search online, I find some general information about neural networks in Mathematica, or a list of related functions. My trouble is ...
- 12.1k
18
votes
2
answers
1k
views
Diffusion probabilistic model in deep generative modeling
Diffusion Models (http://proceedings.mlr.press/v37/sohl-dickstein15.html and https://arxiv.org/abs/2006.11239) are generative models gaining popularity in the community of deep generative modeling, ...
- 835
14
votes
1
answer
918
views
Neural machine translation model using deep learning
In Mathematica version 11.1, SequenceAttentionLayer is introduced to model attentions in the recurrent neural network. It has been shown that attention mechanism ...
- 27.8k
13
votes
2
answers
524
views
Simple example of NetGraph running in MXNet?
There is an great example of exporting a NetGraph (that was trained in Mathematica) into the MXNet's format.
However, I think there's a bug or something is wrong with the answer, because once ...
- 3,820
13
votes
2
answers
790
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, ...
- 31.8k
13
votes
2
answers
3k
views
How to train a convolutional neural net on images?
The functions Predict[] and Classify[] both have the option Method -> "NeuralNetwork", ...
- 31.8k
13
votes
1
answer
9k
views
How can image segmentation from UNET be improved?
EDIT 2: code can be found @ https://github.com/alihashmiii/UNet-Segmentation-Wolfram
EDIT 1: applying Binarize to the masks after resizing helps to ensure the data for mask is binary
I have made an ...
- 9,060
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
11
votes
1
answer
870
views
How to use an external GPU to train neural networks in Mathematica?
Taking steps in the uncharted territories of eGPUs, I have installed an NVIDIA GeForce Titan Xp GPU on an eGPU enclosure (Mantiz MZ-02) and have connected it to my laptop (HP Spectre x360 - 15-bl075nr ...
- 1,883
11
votes
3
answers
994
views
Using Mathematica wlnet model in C++
Suppose if there is a trained net:
SeedRandom[1234];
net = NetInitialize@NetChain[{5, 3}, "Input" -> 2];
It can predict image in mma:
...
- 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
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
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
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
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
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
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
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
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.
...
- 65k
7
votes
1
answer
195
views
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
0
answers
186
views
How can I prevent errors with ReplicateLayer[]?
I am trying to build a NetGraph[] that takes input of the form {{0.6},{0.6},...,{0.8},{0.8}} and multiplies the last sequence ...
- 1,447
5
votes
0
answers
145
views
Can I extract symbolic expression of neural network loss function?
Once we create a neural network with NetChain in Mathematica, can we extract the loss function in the symbolic form for Mathematica to play with symbolic manipulations using Mathematica's built-in ...
- 1,249