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

MXNet HybridBlock model parallelism

I am new to MXNet and have been experimenting with model parallelism. I found this nice post: simple example of mxnet model parallelism and modified the code to use HybridBlock as follows: import numpy as np import mxnet as mx from mxnet import nd,…
Hugo
  • 21
  • 2
0
votes
1 answer

how to use mxnet in python

I trained a cnn in mathematica using the network lenet und exported it as MXnet. How can I use the exported JSON and PARAMS in python to predict? How to load the model? I could not find useful examples or documentation for this. I am using python…
user3483676
  • 177
  • 1
  • 8
0
votes
1 answer

MXNet - Augmentations - expected uint8, got float32

I am attempting to use mxnet 1.10/mxnet-cu91 for image classification. I am currently attempting to use mxnet.image.ImageIter to iterate through and preprocess images. I have been able to successfully use the Augmenters to preprocess the images,…
DFenstermacher
  • 564
  • 1
  • 9
  • 23
0
votes
1 answer

Calculating Cosine Distance in MXNet

I want to be able to calculate the cosine distance between row vectors using MXNet. Additionally I am working with batches of samples, and would like to calculate the cosine distance for each pair of samples (i.e. cosine distance of 1st row vector…
Thom Lane
  • 993
  • 9
  • 9
0
votes
1 answer

Fine tuning on MXNet other than FC layers

Im new to MXNet and I was wondering if any one knows how to fine tune more layers in CNN other than only the FC layers. All the examples that Im looking at, have fine tuning only on the FC layers. In Keras this can be easily done and more blocks of…
Azi
  • 21
  • 3
0
votes
1 answer

how can I use mxnet warpctc in right dimension

FC = mx.sym.FullyConnected(data=x_3,flatten=False, num_hidden=n_class) x = mx.sym.softmax(data=FC) sm_label = mx.sym.Reshape(data=label, shape=(-1,)) sm_label = mx.sym.Cast(data = sm_label, dtype = ‘int32’) sm = mx.sym.WarpCTC(data=x,…
Ming
  • 71
  • 1
  • 1
  • 6
0
votes
1 answer

MxNet metrics API to compute accuracy for multiclass logistic regression with vector labels

How to use MxNet metrics api to calculate accuracy of the multiclass logistic regression classifier with vector labels? Here is an example for labels: Class1: [1,0,0,0] Class2: [0,1,0,0] Class3: [0,0,1,0] Class4: [0,0,0,1] The naive way to use this…
Dimon Buzz
  • 1,130
  • 3
  • 16
  • 35
0
votes
1 answer

Why normalizing labels in MxNet makes accuracy close to 100%?

I am training a model using multi-label logistic regression on MxNet (gluon api) as described here: multi-label logit in gluon My custom dataset has 13 features and one label of shape [,6]. My features are normalized from original values to [0,1] I…
Dimon Buzz
  • 1,130
  • 3
  • 16
  • 35
0
votes
1 answer

How to realize Tensorflow/MXNet reduce_mean operations on the specific axes in Caffe

I encountered a problem when try to convert the MXNet model to Caffe model. I find a nodes operation in MXNet that defined as "op"="mean", which seems not been perfectly supported in Caffe. MXNet Node: { "op": "mean", "name": "mean0", …
oscarriddle
  • 51
  • 6
0
votes
1 answer

MxNet for Embedded device inference

Is there a way to take MxNet model adn deploy it to embedded device directly? As "embedded", objective is to have super lightweight, optionally optimized for ARM/neon.
krishnakamathk
  • 143
  • 2
  • 9
0
votes
1 answer

Limit number of CPUs using MXNET

How can I set the number of CPUs to use in MXNET Gluon to a certain number, say 12? I don't see the answer in the documentation anywhere and by default MXNET uses all the CPUs.
Maturin
  • 387
  • 1
  • 4
  • 14
0
votes
1 answer

how to do image classification with MXNet?

I just got started with MXNet, and I have wrote and trained a CNN with MNIST based on some tutorials. Now I wish to actually send a picture to this CNN and get a result from it, how should I do it? Here're my code: def get_lenet(): data =…
Woooooooo
  • 85
  • 1
  • 2
  • 7
0
votes
1 answer

Does MXNet read training data from S3 in a streaming fashion?

This page talks about reading training data from S3 bucket directly. Does anybody know if the data is read in a streaming fashion or if the entire training data is copied to a local cache before training begins?
Indhu Bharathi
  • 1,437
  • 1
  • 13
  • 22
0
votes
2 answers

MxNet with R: Simple XOR Neural Network is not learning

i am wanted to experiment with the MxNet library and built a simple neural network which learns the XOR function. I am facing the problem, that the model is not learning. Here is the complete script: library(mxnet) train = matrix(c(0,0,0, …
vaka
  • 33
  • 7
0
votes
1 answer

mxnet ndarray iterator for C++

I would like to train a simple classifier in C++, very much in the fashion of the C++ mnist example, where however my data is not stored on the HD but already loaded to the memory, say to an mxnet NDArray. In Python for this purpose one has the…
Gilb0
  • 1
  • 2
1 2 3
…
46 47