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
26
votes
2 answers

What is the proper way to weight decay for Adam Optimizer

Since Adam Optimizer keeps an pair of running averages like mean/variance for the gradients, I wonder how it should properly handle weight decay. I have seen two ways of implementing it. Only update mean/variance from the gradients based on the…
Kato
  • 478
  • 1
  • 5
  • 8
19
votes
2 answers

Parallelization strategies for deep learning

What strategies and forms of parallelization are feasible and available for training and serving a neural network?: inside a machine across cores (e.g. GPU / TPU / CPU) across machines on a network or a rack I'm also looking for evidence for how…
Josh
  • 11,979
  • 17
  • 60
  • 96
15
votes
1 answer

Nvidia GPU memory allocated but by no process?

I am frequently rerunning the same mxnet script while I try to iron out some bugs in a new script (and I am new to mxnet). Pretty often when I try to run my script I get an error that the GPU is out of memory, and when I use nvidia-smi to check,…
TFdoe
  • 571
  • 5
  • 16
15
votes
5 answers

Sudden drop in accuracy while training a deep neural net

I am using mxnet to train a 11-class image classifier. I am observing a weird behavior training accuracy was increasing slowly and went upto 39% and in next epoch it went down to 9% and then it stays close to 9% for rest of the training. I restarted…
sau
  • 1,316
  • 4
  • 16
  • 37
15
votes
2 answers

How to increase validation accuracy with deep neural net?

I am trying to build a 11 class image classifier with 13000 training images and 3000 validation images. I am using deep neural network which is being trained using mxnet. Training accuracy is increasing and reached above 80% but validation accuracy…
sau
  • 1,316
  • 4
  • 16
  • 37
11
votes
1 answer

Why are deep learning libraries so huge?

I've recently downloaded all packages from PyPI. One interesting observation was that of the Top-15 of the biggest packages, all execept one are deep learning packages: mxnet: mxnet-cu90 (600 MB), mxnet-cu92, mxnet-cu101mkl, mxnet-cu101 (and 6 more…
Martin Thoma
  • 124,992
  • 159
  • 614
  • 958
11
votes
3 answers

Is there a way to check if mxnet uses my gpu?

Can I see what are the available GPUs with mxnet? Is there something similar for TensorFlow's tf.test.gpu_device_name() in mxnet?
Ștefan
  • 773
  • 2
  • 7
  • 19
11
votes
1 answer

Maximize tensorflow multi gpu performance

I was wondering if anybody could advise on how to get peak performance out of tensorflow in a 4 GPU setting. As a test I created two of the same network (18 ish layer residual network with small filter banks (ranging from 16-128) on 32x32 inputs.…
luke
  • 1,024
  • 3
  • 11
  • 21
10
votes
3 answers

What are all the formats to save machine learning model in scikit-learn, keras, tensorflow and mxnet?

There are many ways to save a model and its weights. It is confusing when there are so many ways and not any source where we can read and compare their properties. Some of the formats I know are: 1. YAML File - Structure only 2. JSON File -…
superduper
  • 401
  • 1
  • 5
  • 16
10
votes
1 answer

How to build a model in MXNet using matrices and matrix operations explicitly?

I can create a model using the pre-build high-level functions like FullyConnected. For example: X = mx.sym.Variable('data') P = mx.sym.FullyConnected(data = X, name = 'fc1', num_hidden = 2) In this way I get a symbolic variable P that is dependent…
Roman
  • 124,451
  • 167
  • 349
  • 456
9
votes
1 answer

Using ROIPooling layer with a pretrained ResNet34 model in MxNet-Gluon

Assume I have a Resnet34 pretained model in MXNet and I want to add to it the premade ROIPooling Layer included in the API: https://mxnet.incubator.apache.org/api/python/ndarray/ndarray.html#mxnet.ndarray.ROIPooling If the code for initializing…
obelix
  • 880
  • 2
  • 16
  • 43
8
votes
1 answer

How to retrieve the labels used in a segmentation mask in AWS Sagemaker

From a segmentation mask, I am trying to retrieve what labels are being represented in the mask. This is the image I am running through a semantic segmentation model in AWS Sagemaker. Code for making prediction and displaying mask. from…
Dre
  • 713
  • 1
  • 8
  • 27
8
votes
1 answer

LSTM example to time series prediction via MXNet in R

Does anybody know where can I find an example of LSTM via MXNet (R package)? The basic task is prediction of x[t + 1] value by x[1 ... t] sequence.
sermal
  • 93
  • 1
  • 6
7
votes
2 answers

How can I use the gluon-cv model_zoo and output to an OpenCV window with Python?

My code is: import gluoncv as gcv net = gcv.model_zoo.get_model('ssd_512_mobilenet1.0_voc', pretrained=True) windowName = "ssdObject" cv2.namedWindow(windowName, cv2.WINDOW_NORMAL) cv2.resizeWindow(windowName, 1280, 720) cv2.moveWindow(windowName,…
Shamoon
  • 41,293
  • 91
  • 306
  • 570
7
votes
3 answers

MXNet package installation in R

I get plenty of trouble when trying to install MXNet package in R I am using the 3.4.0 version of R and I am on windows 10 CPU intel i3, 64bits x64-based processor. I get prompted: install.packages("mxnet") Warning in install.packages : cannot…
Gotey
  • 449
  • 4
  • 15
  • 41
1
2 3
…
46 47