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

Decoder Input in Seq2Seq - Time Series Analysis

I'm working with MxNet and I'm figuring out the Seq2Seq model. Let’s suppose that every batch will handle 32 sequences and every sequence will be of length 20 (timesteps). In order to create the architecture to work with seq2seq models we are going…
BloomShell
  • 833
  • 1
  • 5
  • 20
0
votes
0 answers

MXNET Evaluating predictions against MNIST dataset

I have trained MNIST model using Lenet CNN and now I am trying to evaluate some input images against the trained network. The training and evaluation were good as it reached 0.963241 accuracy after 100 epochs. [03:20:24]…
Greg
  • 1,671
  • 2
  • 15
  • 30
0
votes
0 answers

Problem with gluoncv Object Detection "Train Faster-RCNN end-to-end on PASCAL VOC" example

I'm new on gluon and I decided to run the examples to get familiar with the coding style (I used keras a couple years ago and this hybrid style is a little bit confusing to me). My problem is that I can run the examples, but after successfully…
JPabloFuenzalida
  • 81
  • 1
  • 10
0
votes
1 answer

Regression using MXNet

I have a regression model based on various independent features which eventually predict a value with a custom loss function. Somewhat similar to the link…
Abhishek Srivastava
  • 13
  • 1
0
votes
0 answers

How to limit number of Core utilization by GluonCV

I am trying same GluonCV inferencing examples. However I want to benchmark the results on a single core. I tried to play with ctx gave cpu(0) but still unable to limit the number of cores which are getting utilized. I Tried the following it works…
Scorpio
  • 511
  • 4
  • 14
0
votes
1 answer

ImageNet Classification: np.testing.assert_almost_equal(pred_probas.sum().asscalar(), 1, decimal=5)

For Image Classification in Mxnet using GluonCV Model, I am using a transformed image through the network to obtain predicted probabilities for all ImageNet classes. def predict_probabilities(network, data): """ Should return the predicted…
Zargham Khan
  • 1
  • 1
0
votes
1 answer

How to install the mxnet-1.4.1(CPU-Version) offline in Windows 10 stackoverflow?

I want to try 'GluonTS - Probabilistic Time Series Modeling in Python'.And GluonTS is a Python toolkit for probabilistic time series modeling, built around Apache MXNet (incubating). I must install MXNet 1.4.1, then install GluonTS to try use…
user10716938
  • 53
  • 4
0
votes
1 answer

How to perform pixelwise normalization on an image

I am trying to perform pixel-wise normalization, but I dont understand the concept or how to implement it. I have the MNIST Fashion data set, I have performed mean normalization on all the 1024 images. # Assuming all images are the same size, get…
Oscar Rangel
  • 848
  • 1
  • 10
  • 18
0
votes
1 answer

Probabilistic time series returning results above thresholds (GluonTS)

I have a dataset with an upper numerical limit of 50, none of the samples go above this figure or below zero. After running a deepAREstimator in GluonTS I get predictions way above 50 and also in the minuses. How can/could I fix this?
G Gr
  • 6,030
  • 20
  • 91
  • 184
0
votes
1 answer

How to make inference on local PC with the model trained on AWS SageMaker by using the built-in algorithm Semantic Segmentation?

Similar to the issue of The trained model can be deployed on the other platform without dependency of sagemaker or aws service?. I have trained a model on AWS SageMaker by using the built-in algorithm Semantic Segmentation. This trained model named…
Zhen Wang
  • 61
  • 1
  • 5
0
votes
1 answer

GluonCV - Export object detection models to Android

I’ve been using GluonCV for object detection, and I was trying to figure out how to export these models to Android (I re-trained a few models on my own dataset, so I’d like to export those). I’m really new to the topic, so I was looking for a place…
Carlo
  • 1,321
  • 12
  • 37
0
votes
1 answer

How to use .rec format for training in MXNet C++ implementation?

C++ examples of MXNet contain model training examples for MNISTIter, MNIST data set (.idx3-ubyte or .idx1-ubyte). However the same code actually recommends to use im2rec tool to produce the data, and it produces the different .rec format. Looks like…
Audrius Meškauskas
  • 20,936
  • 12
  • 75
  • 93
0
votes
1 answer

What is correct input for mxnet's linear learner in AWS SageMaker?

I am trying to create a simple linear learner in AWS SageMaker with MXNet. I have never worked with SageMaker or MXNet previously. Fitting the model gives runtime error as follows and shuts the instance: UnexpectedStatusException: Error for…
vivekpadia70
  • 1,039
  • 3
  • 10
  • 30
0
votes
1 answer

Rotating image and load to MXNet model

Is there a way to load a image, rotate it and load it to MXNet model (e.g: yolov3). I use the below method but I don't think it's efficient: 1/ Load the image and rotate it with pillow image = Image.open(img_path) image = image.rotate(90) 2/ Save…
manaclan
  • 816
  • 9
  • 20
0
votes
1 answer

why normalization do not need parameters, but batch normalization need

Normalization is just normalizing the input layer. while batch normalization is on each layer. We do not learn parameters in Normalization But why we need to learn the batch normalization?
jinxinhelloworld
  • 97
  • 2
  • 8
1 2 3
…
46 47