Skip to main content
27 votes

How to export an MXNet?

It seems the model file in MXNet (checkpoint) is defined by two files: a ".json" file and a ".params" file. The json file contains the definition of the network, and the params file contains the ...
xslittlegrass's user avatar
8 votes

Example of NetChain running in MXNet cause Error

I will make a complete example of making predictions with exported nets in MXNet (Python binding). First, ...
Sebastian's user avatar
  • 3,479
6 votes

Export BatchNormalizationLayer as MXNet

I found the following workaround for NetChains with several Batchnorm layers by manually exporting aux states: Mathematica ...
MaxJ's user avatar
  • 1,535
6 votes

Using Mathematica wlnet model in C++

In Mathematica 11.2, which will be released in the next month or so, it is as simple as writing Export["mynet.json", net, "MXNet"]. This will also produce a "params"...
Taliesin Beynon's user avatar
5 votes
Accepted

Simple example of NetGraph running in MXNet?

In my question Example of NetChain running in MXNet cause Error and re-post in Wolfram Community Thanks for Mike Sollami gave nice code to get the perfect result.
partida's user avatar
  • 6,836
5 votes
Accepted

Using Mathematica wlnet model in C++

I will use two cases to make example: First,Seq2Seq model RandomSeed[1234]; net = NetInitialize@NetChain[{5, 3}, "Input" -> 2]; net[{1,2}] {1.27735, -1....
partida's user avatar
  • 6,836
5 votes
Accepted

NetTrain with multi-label data?

Make your data multi-hot: dataMultiHot = MapAt[Total@*NetEncoder[{"Class", allLabels, "UnitVector"}], data, {All, 2}] Use ...
swish's user avatar
  • 7,921
5 votes
Accepted

Export BatchNormalizationLayer as MXNet

This is fixed in Mathematica 12.0: ...
Stefan R's user avatar
  • 2,236
4 votes
Accepted

Can't import Gluon into mma

Bug fixed in 11.3.0 net = Import[ "C:\\Users\\xzhou\\Desktop\\mxnet_prediction\\SE\\model.json", "MXNet"] net[{0.1, 0.2, 0.3}]
partida's user avatar
  • 6,836
4 votes

Can't import Gluon into mma

In Mathematica 11.2, this code will crash the kernel, I think because mma use old version of MXNet This hypothesis is correct. I have verified that this works for internal 11.3 builds which use the ...
Sebastian's user avatar
  • 3,479
4 votes

Error Import a MXNet model Export by Mathematica in 11.2 and 11.3

There are two function GeneralUtilities`MLExport and GeneralUtilities`MLImport to do export and import thing.But it cannot ...
yode's user avatar
  • 26.8k
3 votes

How can I reproduce the result of AgeEstimation model in MXNet-Python?

I get a better result if I use FindFaces as a basis to crop the image. Get the same image and net model that you're using: ...
Brett Champion's user avatar
2 votes

how to import mathematica trained mxnet neural net

When you export the model, you will get a "json" and "params" file. You can then follow these steps to load the files and import the model into Python: ...
NRauschmayr's user avatar
2 votes

Example of NetChain running in MXNet cause Error

After some try and error. I found there are at least two methods to load a mathematica-exported mxnet-model to predict and get the result. I think some is bug of MXNet and some is bug of Mathematica....
HyperGroups's user avatar
  • 8,619
2 votes

Example of NetChain running in MXNet cause Error

I have the right way to do that, after hours of work! The right way, is to modify the exported file from Mathematica to have them compliant with the standard MXNet. The params file obtained by ...
tonegas's user avatar
  • 393
1 vote

Error Training FeedForward Neural Network With Various Type of Variables

I found the answer in another link: ...
user34018's user avatar
  • 869
1 vote

Is Mathematica's implementation of convolutional neural networks really inefficient?

Exploration of the problem. This is not an answer. ...
Alexey Golyshev's user avatar
1 vote
Accepted

3D Deconvolutional Layer

I found the following solution using convolutional layers and reshape layers on the community page: https://community.wolfram.com/groups/-/m/t/1344787
MaxJ's user avatar
  • 1,535
1 vote

Using Mathematica wlnet model in C++

The right fix for the params file is this, it is fully exaplained in https://mathematica.stackexchange.com/a/162479/54287. The params file obtained by Mathematica misses of the string "arg" at the ...
tonegas's user avatar
  • 393
1 vote

Simple example of NetGraph running in MXNet?

The best way to do that, it is change the way of exporting by Mathematica and it is fully explained in https://mathematica.stackexchange.com/a/162479/54287
tonegas's user avatar
  • 393
1 vote
Accepted

Custom NetEncoder for lower resolution image input in a pre-trained Inception network

Netencoders of type image will automatically upsample or downsample images to the size specified in the netencoder function. You cannot change the size of the network input, as classifier at the end ...
Yss's user avatar
  • 278

Only top scored, non community-wiki answers of a minimum length are eligible