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
3
votes
1 answer

MXNET custom loss function and eval_metric

How do I create a custom loss function in MXNET? For example, instead of computing cross-entropy loss for one label (using standard mx.sym.SoftmaxOutput layer which computes cross-entropy loss and returns a symbol that can be passed as a loss symbol…
Ashish Khetan
  • 121
  • 1
  • 6
3
votes
1 answer

Custom MXNet Operators and kAddTo

I'm a writing a C++ custom operator in MXNet and am having trouble finding documentation on when kAddTo is set in an operator invocation. As a minimal example, let's say that my new operator is called foo() and I want to perform the following…
Chris Swierczewski
  • 679
  • 6
  • 24
3
votes
1 answer

Apparently contradictory results from topk/sort and pick

I'm predicting roughly one of 100K possible outputs with a MXNet model, using a fairly standard softmax output. I want to compare the probability assigned to the true label versus the top predictions under the model. To get the former I'm using the…
Ben Allison
  • 7,244
  • 1
  • 15
  • 24
3
votes
2 answers

Ubuntu - Error while running program in python: "ImportError: No module named mxnet"

I am trying to install the new MXNet from validate-mxnet-installation. I followed the instructions (I chose options Linux->python->GPU->pip ) as you can see on the website and they were: install cuda8 from nvidia website install cuDNN 5 library…
Davis8988
  • 298
  • 4
  • 16
3
votes
1 answer

How to use adapted learning rate in MxNet

Learning rate is the key to the effect of my network. When I define lr = 0.05, the train/validation-accuracy oscillate severely, however lr = 0.025 I cann't get any effect until Epoch[30]. So I remember the adapted learning rate in caffe, at first I…
Lolith
  • 33
  • 2
3
votes
2 answers

android-ndk: stoi / stof / stod / to_string is not a member of 'std'

I was compiling mxnet(v0.9.3) amalgamation with android NDK Standalone Toolchain on Ubuntu 14.04 64bit Desktop but met some errors. First error is: arm-linux-androideabi-g++ -std=c++11 -Wall -O3 -msse2 -Wno-unknown-pragmas -funroll-loops -Iinclude…
ROKIM
  • 53
  • 1
  • 6
3
votes
1 answer

Recurrent Neural Networks for Panel Data

There are 2 parts to this question. Suppose we are looking at sales S of a product across $> 1000$ stores where a it sells. For each of these 1000 stores we have 24 months recorded data. We want to be able to predict S_t <- f(S_{t-1}). We could…
Sandipan Bhattacharyya
  • 137
  • 2
  • 14
3
votes
1 answer

Poor performance of mxnet LinearRegressionOutput

I have been unable to get reasonable performance using mxnet LinearRegressionOutput layer. The self-contained example below attempts to perform regression of a simple polynomial function (y = x1 + x2^2 + x3^3) with a small amount of random noise…
kabdulla
  • 5,199
  • 3
  • 17
  • 30
3
votes
1 answer

MXNet initialization error on label variable

When I call module.fit() I'm getting an error ValueError: Unknown initialization pattern for labelidx. The symbol "labelidx" is the name I'm using for my label data -- I didn't want to use softmax_label because I'm not using softmax output, but that…
Leopd
  • 41,333
  • 31
  • 129
  • 167
3
votes
1 answer

How to interpret this scala syntax "Class[_ >: Float with Int with Double]"

When I read Mxnet source code, I was confused in following statements: object NDArray { private val logger = LoggerFactory.getLogger(classOf[NDArray]) private[mxnet] val DTYPE_NATIVE_TO_MX: Map[Class[_ >: Float with Int with Double], Int] =…
David Wang
  • 31
  • 1
3
votes
2 answers

Reshaping OpenCV Image (numpy) Dimensions

I need to convert an image in a numpy array loaded via cv2 into the correct format for the deep learning library mxnet for its convolutional layers. My current images are shaped as follows: (256, 256, 3), or (height, width, channels). From what I've…
AdmiralJonB
  • 2,038
  • 3
  • 23
  • 27
3
votes
1 answer

How can I feed .csv training data to a convolutional neural network in mxnet?

I recently installed mxnet (python package) with GPU support on Windows 10 and Python 3.5. I run through a couple of examples and they seem to work fine. I am used to scikit-learn style machine learning packages and very new to Python deep learning…
mickkk
  • 1,172
  • 2
  • 17
  • 38
3
votes
2 answers

is there concept about multiplecpu in mxnet

As we know, there is concept about multiplegpu in mxnet,when specify -gpu in command.And if we don't specify gpu,it will run it on cpu.How many cpus do it run ?Can it possible to specify multiple cpu?
刘米兰
  • 183
  • 2
  • 11
3
votes
1 answer

MXNET vs Theano Experience

Am looking to do some distributed calc. using GPU for machine learning ? Just wondering if anybody has experience with MXNET (perf. vs Theano) Reference http://www.cs.cmu.edu/~muli/file/mxnet-learning-sys.pdf Thanks
user5497885
2
votes
0 answers

mxnet: CUDA Check failed: e == cudaSuccess (803 vs. 0) : system has unsupported display driver / cuda driver combination

As mxnet nvidia froums and github does not answer questions properly and also they don't have good community like stackoverflow I ask this question here. Host: Linux XYZ 5.15.0-76-generic #83~20.04.1-Ubuntu SMP Wed Jun 21 20:23:31 UTC 2023 x86_64…
gunner gunner
  • 21
  • 2
1 2 3
…
46 47