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 fine-tune save model

I'm using mxnet's fine-tune example to fine-tune my own data with this code: https://github.com/dmlc/mxnet/blob/master/example/image-classification/fine-tune.py By viewing common/fit.py, I got no idea of how to save temp model when I fine…
D.Ding
  • 23
  • 1
0
votes
1 answer

Define a customized operation in MXNetR

I am creating a network using mxnetR and want to create a customized operator. I look at the mx.symbol.Custom function in the package and the description says that I should use a front end language like Python to define my operation. I found a…
nnguyen24
  • 21
  • 1
  • 4
0
votes
1 answer

Error related to data shape when running MXNetR

I am trying to build a Feed Forward neural network with MXNetR. My input is a data frame with 6380 rows and 180 columns. My training and testing outputs are one-dimensional vectors with 319 elements each. I run the model with the batch size set to 1…
nnguyen24
  • 21
  • 1
  • 4
0
votes
1 answer

confused about sum_axis in mxnet in the tutorial

I am reading the mxnet tutorial on NDarray part and I am confused about the use of sum_axis function and the example is : >>> a = mx.nd.ones((2,3)) >>> c = mx.nd.sum_axis(a, axis=1) >>> c.asnumpy() array([ 3., 3.], dtype=float32) >>> c =…
ningyuwhut
  • 609
  • 12
  • 27
0
votes
1 answer

MxNet: Accuracy falls to random prediciton after some iterations

When I was training a CNN to classify images of distorted digits varying from 0 to 9, the accuracy of training set and test set improved obviously. Epoch[0] Batch [100] Train-multi-accuracy_0=0.296000 ... Epoch[0] Batch [500]…
Lolith
  • 33
  • 2
0
votes
1 answer

MXNet: Are there python api to get some op`s name

I want to see what is the op's type/name of one Symbol in MXNet. e.g: c = mxnet.symbol.Convolution() type(c) --> will print this symbol is Convolution or others like Pooling etc.
daiab
  • 1
0
votes
2 answers

hoot upgrade to the pre-release package of mxnet

I want to upgrade to the pre-release package of mxnet pre. Can i do this through pip? I tried pip with --pre --upgrade. This installed the latest official release. Is there a way where I can upgrade to the pre-release version. i am using mac os
MAS
  • 4,503
  • 7
  • 32
  • 55
0
votes
1 answer

Does MXNET has auto-differentiation feature?

Mxnet and Tensorflow both declare that they has auto-differentiation feature. In Mxnet, I need to define the backward part when creating a new op(like loss function), but not in Tensorflow. In my knowledge, auto-differentiation means I don't need to…
Zehao Shi
  • 99
  • 8
0
votes
1 answer

Facing difficulties in regression with mxnet in R

I was following this tutorial http://mxnet.io/tutorials/r/fiveMinutesNeuralNetwork.html#regression Everything worked accordingly but when I changed: fc1 <- mx.symbol.FullyConnected(data, num_hidden=1) to fc1 <- mx.symbol.FullyConnected(data,…
Ruhshan
  • 121
  • 1
  • 8
0
votes
1 answer

Error with LSTM RNN in mxnet (R environment)

I'm trying to setup a LSTM RNN by using mxnet in R, however, while trying to train my network I get this error and R is showing me a fatal error all the time: "[00:36:08] d:\program files…
Yurii Malna
  • 1
  • 2
0
votes
1 answer

How to predict the labels for the test set when using a custom Iterator in MXnet?

I have a big dataset (around 20GB for training and 2GB for testing) and I want to use MXnet and R. Due to lack of memory, I search for an iterator to load the training and test set by a custom iterator and I found this solution. Now, I can train…
Mohammad
  • 1,006
  • 2
  • 15
  • 29
0
votes
2 answers

Is there any toy example of building convolutional autoencoders using MxNet?

I'm looking for implementations of convolutional autoencoder using MxNet. But there is only one example of autoencoder based on Fully Connected Networks, which is here. There is also an issue asking similar questions in github, but receives very few…
pfc
  • 1,831
  • 4
  • 27
  • 50
0
votes
1 answer

MXNet R version CUDA failure on AWS ec2(ubuntu14.04)

I am trying to install MXNet R version on Amazon Web Service EC2 (ubuntu 14.04LTS) by following the instruction: http://mxnet.io/get_started/ubuntu_setup.html. First I downloaded CUDA 8toolkit from nvidia. sudo dpkg -i…
Kang Daniel
  • 1
  • 2
0
votes
1 answer

mxnet custom activation function / op in numpy

I have a question regarding the syntax used in creating a custom activation function / op in mxnet. I was looking at this example: https://github.com/dmlc/mxnet/blob/master/example/numpy-ops/custom_softmax.py Specifically, this part: class…
darius
  • 3
  • 1
0
votes
1 answer

pack individual .jpg image files into RecordIO (.rec) files

I'm trying to go through the MXNET tutorial (https://statist-bhfz.github.io/cats_dogs_finetune), but have trouble making the RecordIO ".rec" files used to process the pictures. I have tried the suggested approach: python…
Daniel Safai
  • 45
  • 1
  • 7
1 2 3
…
46 47