Questions tagged [mxnet-format]
Questions involving executing and importing neural networks from MXNet.
26
questions
3
votes
0
answers
110
views
What will be the next backend for machine learning?
Apache MXNet has been the choice of Mathematica Neural Network backend, but it has long since been mostly ignored by the ML community and now is finally in the attic (https://attic.apache.org/projects/...
18
votes
0
answers
734
views
Neural Network Automatic Differentiation ("Autograd")
Automatic differentiation methods in general have been the topic of past questions, but this is specifically about automatic differentiation of neural networks.
The motivation is an old but useful ...
2
votes
0
answers
57
views
HPC doesn't read .mx file
I am trying to work in an HPC cluster. Mathematica works fine and I can export tables that I need. However, I had one interpolated data saved in as a mx file. I ...
6
votes
0
answers
118
views
Fail to Export/Import seq2seq model (NER) to MXNet or ONNX
Mathematica 12.2 on Linux (Debian)
Here's a simple Named Entity Recognition model:
...
1
vote
0
answers
80
views
Importing A Neural Network From Mathematica For Use In R
I am experimenting with platform interoperability between Mathematica and R.
My aim is to create an untrained Neural Network using Mathematica, export this network in MXNet format as a .json file, ...
0
votes
0
answers
128
views
Use FacialFeatures in Python Web API?
Under the hood, FacialFeatures uses the net-model ResNet-101 Trained on Augmented Casia WebFace Data. I would like to see a tutorial-style answer on how one would ...
0
votes
0
answers
98
views
No progress on validation NN training set
So in short my issue is that I'am training a neural network and while the training loss reduces over time, the loss of validation set remains constant.
The progress of training looks like this:
I am ...
6
votes
0
answers
169
views
Export ImageCases to Python?
I’d like a tutorial on how to export a bounding box detector network to mxnet, (for bonus points: convert to Tensorflow), and then get it running correctly in python!
Some related questions exist for ...
5
votes
1
answer
119
views
Error Training FeedForward Neural Network With Various Type of Variables
I built the following FeedForward NN
...
8
votes
1
answer
243
views
Is Mathematica's implementation of convolutional neural networks really inefficient?
I'm surprised how slow ConvolutionLayer works with TargetDevice->"CPU". For instance this code:
...
2
votes
1
answer
112
views
3D Deconvolutional Layer
I noticed that one of the mxnet APIs (Gluon) includes a 3D Deconvolutional Layer. However, mathematica currently only allows up to 2D deconvolutional layers (see here). Can one somehow implement a 3D ...
10
votes
0
answers
763
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.
...
1
vote
1
answer
334
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
3
votes
0
answers
138
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, ...
4
votes
1
answer
159
views
How can I reproduce the result of AgeEstimation model in MXNet-Python?
How can I reproduce the result of AgeEstimation model in MXNet-Python?
here is my repo about MXnet-Python codes to load Mathematica Models.
I want the result of Mathematica and the result of MXNet-...
4
votes
2
answers
295
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
0
answers
221
views
Is is a bug when importing MXNet model?
There is a trained net:model.zip
Using Python to make prediction:
...
3
votes
0
answers
262
views
11
votes
2
answers
343
views
Export BatchNormalizationLayer as MXNet
Bug introduced in 11.2 and remains in 12.0.0
I just tried to import a net from mathemtica into pythons using MXNet. It works fine with the following manual.
However, as soon as I try to add a ...
8
votes
2
answers
303
views
Can't import Gluon into mma
This is a simple DNN from Fast, portable neural networks with Gluon HybridBlocks:
This is json file and params file of Gluon(MXNet)
...
5
votes
1
answer
266
views
Error Import a MXNet model Export by Mathematica in 11.2 and 11.3
the model was trained by
net = NetModel["Inception V1 Trained on ImageNet Competition Data"]
...
9
votes
3
answers
926
views
Example of NetChain running in MXNet cause Error
Cross post here
Problem remains in Mathematica 11.2
First defining the net
...
11
votes
3
answers
987
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:
...
13
votes
2
answers
518
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
votes
1
answer
358
views
Custom NetEncoder for lower resolution image input in a pre-trained Inception network
I have come across this neat explanation on how to adjust a pre-trained Inception neural net to an arbitrary number of classes by truncating the top layers.
However, my input data does not come in $...
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 ...