Stack Overflow
Stack Overflow

Questions tagged [mxnet]

Apache MXNet is a fast, scalable, open source deep learning framework that supports Python, R, Scala, C++, Julia, Go, and Javascript. MXNet can run on multiple CPUs and multiple GPUs distributed across multiple hosts, with almost linear scalability.

Apache MXNet: Flexible and Efficient Library for Deep Learning

For more details see http://mxnet.io/

Flexible

Supports both imperative and symbolic programming

Portable

Runs on CPUs or GPUs, on clusters, servers, desktops, or mobile phones

Multiple Languages

Supports over 7 programming languages, including C++, Python, R, Scala, Julia, Matlab, Javascript and Perl.

Auto-Differentiation

Calculates the gradient automatically for training a model

Distributed on Cloud

Supports distributed training on multiple CPU/GPU machines, including AWS, GCE, Azure, and Yarn clusters

Performance

Optimized C++ backend engine parallelizes both I/O and computation

701 questions
0
votes
1 answer

How to set some dropout when training a neural network using MxNet?

When training a Deep Convolutional Neural Network using MxNet, what is the simplest way to turn on some amount of dropout in order to reduce overfitting? Is there a way to add a dropout rate without manually implementing dropout in the network…
Pierre-Antoine
  • 7,939
  • 6
  • 28
  • 36
0
votes
1 answer

Install mxnet 0.12.1 on AWS cuda9 deep learning AMI

AWS deep learning AMIs come with mxnet 0.12.0 RC. Apparently this version has a bug that sets random initialization weights to 0. How to I remove the preinstalled mxnet and upgrade? Logged in via SHH as ec2-user, I tried cd src sudo rm -rf mxnet git…
Garglesoap
  • 565
  • 6
  • 18
0
votes
1 answer

Calling CustomCSVIter function using mxnet pacakge in R

I'm trying to train a list of text datasets at the character level (for example, a cat => "a", " ", "c", "a", "t") so that I can classify them with great accuracy. I'm using mxnet package (CNN Network) in R and using crepe model. So to prepare for…
Phillip1982
  • 189
  • 1
  • 2
  • 10
0
votes
1 answer

Is there a resnet implementation using mxnet gluon api?

I am looking for the model file definition for a resnet implementation using the mxnet gluon api. The model zoo only provides pre-trained models: https://mxnet.incubator.apache.org/api/python/gluon/model_zoo.html I am looking for the code…
Raj
  • 1
  • 1
0
votes
1 answer

DLL load failed when installing rcnn of MXNet in Windows10

I have successfully installed MXNet-0.11 in my laptop, whose OS is Windows 10 and GPU is GTX1060. And now I want to install rcnn, I have run the Makefile in the folder example/rcnn in command line using MinGW64. But when I run demo.py, it tells me…
Terence
  • 1
  • 1
0
votes
1 answer

Translate from sae.dnn (deepnet) to mx.mlp (mxnet) error

I'm trying to translate code from deepnet to mxnet, but I'm not sure what am I doing wrong. I'm getting an error message that says: "Error in nn$W[[i -1]] %*% t(post)". requires numeric/complex matrix/vector arguments Calls: neural.predict ->…
PandemicCode
  • 109
  • 1
  • 8
0
votes
1 answer

Training mxnet:mx.mlp

I am trying to reproduce an example from ND Lewis: Neural Networks for time series forecasting with R. If I include the device argument I get the error: Error in mx.opt.sgd(...) : unused argument (device = list(device = "cpu", device_id = 0,…
r.user.05apr
  • 5,356
  • 3
  • 22
  • 39
0
votes
2 answers

Training using mxnet in ipython console of Spyder not working

I'm running the mnist example of mxnet in Spyder IDE. The training does not progress, just as if the learning rate were 0 (see output below). If I run the same file on the console using either python or ipython, it works as expected (seeing…
ziggystar
  • 28,410
  • 9
  • 72
  • 124
0
votes
1 answer

MXNet - application of GANs to MNIST

So this question is about GANs. I am trying to do a trivial example for my own proof of concept; namely, generate images of hand written digits (MNIST). While most will approach this via deep convolutional gans (dgGANs), I am just trying to achieve…
SumNeuron
  • 4,850
  • 5
  • 39
  • 107
0
votes
1 answer

mxnet packages with Rstudio on Virtual machine

I want to install r studio on virtual machine to work with mxnet package. Here is how to configure Rstudio on microsoft azzure linux virtual machine: http://moresi.de/posts/2016-04-02-setting-up-r-studio-server-on-microsoft-azure.html And there is…
Amadeusz Wieczorek
  • 1
  • 2
0
votes
2 answers

Performance Analysis tools for Tensorflow

I am trying to run some machine learning algorithms using Tensorflow, CNTK, and MxNet. Do these frameworks have some specific performance analysis tools especially to profile runtime information ( memory, communication etc.)?
Abid Muslim Malik
  • 21
  • 6
0
votes
1 answer

How to predict a mini-batch examples in C++ of MXNet?

In python interface,we can use a mini-batch examples to make prediction like net([[1,2],[3,4],[5,6]]). But in C++,I can't find a way to do this. Suppose calling the net to predict a single example needs 10ms. If there is 10000 examples needs to make…
partida
  • 501
  • 4
  • 20
0
votes
1 answer

mxnet tutorials unpack requires a string argument of length 8

Recently, I learned mxnet, by following the tutorials in mxnet.io. In Handwritten Digit Recognition, I run the following code: import mxnet as mx mnist = mx.test_utils.get_mnist() It…
West
  • 13
  • 5
0
votes
1 answer

error message learning simple model mxnet

I am getting this error message Error in mx.model.select.layout.train(X, y) : Cannot auto select array.layout, please specify this parameter I am trying to create simple model to understand how things work create data train.x <-…
Jim R
  • 1
  • 2
0
votes
1 answer

how to control kernel as we need in mxnet

eg: in tensorflow we can do it as followed,how can we do the same thing to control kernel in mxnet,(weights = weights * mask),thank you very much. if mask_type is not None: #C mask[:center_h, :, :, :] = 1 if mask_type == 'A': …
zhanlong hao
  • 1
  • 1
1 2 3
…
46 47