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
2
votes
2 answers

How to specify regularization parameter (L1 or L2) for a feed forward neural network in R using the mxnet package?

I am using R mxnet package. Here is the code block that I am currently using. But I am not sure how to specify regularization. dpLnModel <- mx.model.FeedForward.create(symbol = out, X …
AntonySamuelB
  • 143
  • 7
2
votes
1 answer

How can I predict or train network with multi input data in MXnet?

For example Assume the Variables are: inputs_a = mx.sym.Variable('inputs_a') inputs_b = mx.sym.Variable('inputs_b') Assume the network is: inputs_a[batch_size], 100]-->FullyConnected(10)-->outputs_a[batch, 10] inputs_b[batch_size],…
Alex Hex
  • 51
  • 2
2
votes
1 answer

Does the mxnet symbol API support conditional control flow?

I want to add some conditional control in my symbol, it seems that if-else is evaluated in symbol construction time. But I want it to evaluated in symbol run time. a = mx.symbol.Variable(name='a') b = mx.symbol.Variable(name='b') if a>b: c =…
Zehao Shi
  • 99
  • 8
2
votes
0 answers

Text Classification Using a Convolutional Neural Network on MXNet with R

I'm trying to replicate this tutorial from MXNet in R, but have failed to keep track of all the dicts and tuples from Python. I was wondering whether some of you awesome people have had succes doing the same thing and wouldn't mind sharing? Thanks!
Daniel Safai
  • 45
  • 1
  • 7
2
votes
1 answer

mxnet : how to make prediction using a trained RNN model

I'm testing the RNN model of mxnet. The tutorial here does not work and the error message said many functions had been deprecated. I did not find the up-to-date tutorial for RNN. There are still some examples in the mxnet project. But for RNN, the…
pfc
  • 1,831
  • 4
  • 27
  • 50
2
votes
2 answers

Graphviz not drawing graph

I am trying to visualize the neural network graph created by using mxnet inn python. The code is shown below net = mx.sym.Variable('data') net = mx.sym.FullyConnected(data=net, name='fc1', num_hidden=128) net = mx.sym.Activation(data=net,…
Abhishek Kishore
  • 340
  • 2
  • 13
2
votes
1 answer

How to weight observations in mxnet?

I am new to neural networks and the mxnet package in R. I want to do a logistic regression on my predictors since my observations are probabilities varying between 0 and 1. I'd like to weight my observations by a vector obsWeights I have, but I'm…
jgadoury
  • 293
  • 2
  • 13
2
votes
1 answer

could not find function MXSymbolGetAtomicSymbolName

I am getting "could not find function MXSymbolGetAtomicSymbolName" error in windows 10 on Julia command prompt when I enter: julia> using MXNet What should I do to fix this error
Abhishek Kishore
  • 340
  • 2
  • 13
2
votes
1 answer

Build MXNET library for R

I have used R and MXNET and I see that the version of MXNET from the repo is 0.7 I've built 0.93 from Git and I succeded. (adding lots of dependencies and missing libraries. But the thing is that it did not create "mxnet.dll" for R The only output I…
David
  • 55
  • 7
2
votes
1 answer

mxnet for per-pixel image classification/regression

I am looking for best-practice or case studies using R's "mxnet" for the pixel-wise classification of multi-band imagery (RGB, mlutispectral/hyperspectral aerial or satellite remote sensing). Indeed there is bunch of best practise in image tagging…
cathygeo
  • 21
  • 1
2
votes
2 answers

R mxnet create a 3 input 1 output regression with 3x3 hidden layers

I have a CSV file with 4 columns. 3 inputs and one output. Already normalized. I can use nnet and neuralnet to train a network with 3 inputs, 3 hidden layers with 3 nodes each and one output. It works. I would like to do the same with MXNET but the…
David
  • 55
  • 7
2
votes
4 answers

mxnet installation: How to choose python version?

I installed mxnet in linux mint. I use anaconda for python 3.5. I followed the instruction and it was successfully installed. Both mxnet and the anaconda are latest version. However, when I tried the code: import mxnet as mx res =…
fffly
  • 23
  • 1
  • 4
2
votes
1 answer

Can I run a model trained using tensorflow on mxnet?

I have models trained on tensorflow. Can I use mxnet in forward only mode to run these ? https://github.com/dmlc/nnvm says this should be possible in future, but is the support available today ?
datarpit
  • 21
  • 2
2
votes
1 answer

Install error on mxnet

I am trying to install mxnet for use with R Studio on my Windows 10 laptop. I used these instuctions: install.packages("drat", repos="https://cran.rstudio.com") drat:::addRepo("dmlc") install.packages("mxnet") But when I try this: require(mxnet) I…
Bill Qualls
  • 397
  • 1
  • 7
  • 20
2
votes
1 answer

Mxnet RNN Time Series Prediction

I have a block of code that is supposed to build a RNN model with 5 lag variables for an observation of time series data. Here is the code: library(Quandl) key<-"*******************" Quandl.api_key(key) sh_stock_ex <- Quandl("YAHOO/SS_600292",…
Sandipan Bhattacharyya
  • 137
  • 2
  • 14
1 2 3
…
46 47