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

Regression using MXNet in R with image recognition

I am trying to use image recognition to output a regression style number using the mxnet package in R using a CNN. I have used this as the basis of my analysis:…
Ic3MaN911
  • 251
  • 1
  • 2
  • 8
0
votes
1 answer

MXNet - what is python equivalent of getting scala's mxnet networkExecutor.gradDict("data")

Trying to understand some Scala's code on network training in MXNet. I believe you can access gradient on the executor in Scala by calling networkExecutor.gradDict("data"), what would be equivalent of it in Python MXNet? Thanks!
Stanley Kirdey
  • 602
  • 5
  • 20
0
votes
2 answers

I/O performance difference for sequential vs random acess with MxNet data iterators?

I would like to supply to a network many training images that are sampled from a dataset by following certain sampling rules. Now I have two choices: Use the sampling logic to generate a list of images offline, then convert the .lst file to .rec…
J.Doe
  • 3
  • 1
0
votes
1 answer

Mxnet iterator get data from AWS S3

How can I modify the iterator in this example (https://github.com/dmlc/mxnet/blob/master/example/fcn-xs/data.py) to read images from AWS s3. I have .png images in a folder in AWS s3. I tried passing the rootdir as s3://bucketname/folder. I have also…
MAS
  • 4,503
  • 7
  • 32
  • 55
0
votes
1 answer

Training MXNet Faster R-CNN on own data set

I was using the mxnet example for Faster R-CNN on the official GitHub: Faster R-CNN I created my own dataset and adapted the pascal_voc.py file. This included changing the number of classes to 13. The resolution of my pictures is 600*800 pixel, so a…
Max
  • 560
  • 1
  • 9
  • 25
0
votes
1 answer

NameError: name 'predict_from_url' is not defined

I am trying an MXNet tutorial mentioned at http://mxnet.io/tutorials/embedded/wine_detector.html (Section "Running the Model" on a raspberry pi3 using python3.4, specifically the script "inception_predict.py". I managed to fix a couple of issue but…
Aj G
  • 23
  • 5
0
votes
1 answer

Unchanges training accuracy in convolutional neural network using MXnet

I am totally new to NN and want to classify the almost 6000 images that belong to different games (gathered by IR). I used the steps introduced in the following link, but I get the same training accuracy in each round. some info about NN…
Najme Rastegar
  • 21
  • 2
  • 5
0
votes
1 answer

Build libmxnet.dll for windows

I am following http://mxnet.io/get_started/windows_setup.html to generate libmxnet.dll using the prebuild package for windows. I have downloaded the nightly prebuild release from windows here https://github.com/yajiedesign/mxnet/releases packe…
abj
  • 1
  • 1
0
votes
1 answer

Best way to train only predictable samples in the dataset for R MXNet

I have a training set looks something like this. features:categorical/numerical output:binary 1/0 [1] feature[1][1] feature[1][2] ... feature[1][j] [2] feature[2][1] feature[2][2] ... feature[2][j] . . . [i] feature[i][1] feature[i][2] ...…
k-hir
  • 3
  • 2
0
votes
1 answer

translating a mxnet script for python on windows

I am new in python and mxnet, I want to make the example in the link:http://mxnet.io/how_to/finetune.html In the "Prepare data" part, when i run this script: mkdir -p caltech_256_train_60 for i in 256_ObjectCategories/*; do c=`basename $i` …
user3824903
  • 11
  • 3
0
votes
2 answers

Custom op backward

I am writing a custom op, and I got stucked when writing the backward part. When I call out_grad[0].asnumpy() or do any manipulation of the out_grad, the program crash without any error message. I tried fill the in_grad with zeros, the program run…
Zehao Shi
  • 99
  • 8
0
votes
1 answer

MXNet classification in Python always gives the same predictions

What I am trying here is, by using the Tennis Match Statistics Data Set provided here as an input, I made a neural network model that predicts the match results (1 or 0). By following the official mxnet documents, I developed a program below. I…
k-hir
  • 3
  • 2
0
votes
1 answer

When writing a custom op, if the output shape is dynamic, how to define the output of infer_shape function?

I'm now writing a custom op, and it's output shape is dynamic, how to define the output_shape in infer_shape function.
Zehao Shi
  • 99
  • 8
0
votes
1 answer

In Deep Learning "mxnet", restrict number of core (cpu)

The command "ctx=mx.cpu()" is taking all available CPU. How to restrict to use a certain number only - say 6 out of 8 core
Shiv
  • 369
  • 2
  • 13
0
votes
1 answer

Extract Input parameters from "mxnet" model

I have saved the model using mx.model.save(model = fit_dl, prefix = "model", iteration = 10) and loaded later fit <- mx.model.load(prefix = "model", iteration = 10) Now, using object fit, I want to extract the input features (column names of…
Shiv
  • 369
  • 2
  • 13
1 2 3
…
46 47