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

vote

1 answer

Avoiding weight sharing among certain layers in BucketingModule in mxnet?

I am using BucketingModule for training multiple small models/bots together. Here, the bucket key is bot_id. However, each bot has separate set of target labels/classes (and hence, different size of softmax layer for each bot). Is there any way to…

mxnet softmax

asked Dec 12 '17 at 23:22

user9091302

vote

1 answer

how to print out each class's Average Precision using Mxnet Faster RCNN for object detection

I am using faster rcnn(mxnet) for object detection on my own dataset, which has 9 classes(including background). However, i found that in the end it only prints out the average accuracy over all 9 classes during trainning process. Furthermore,…

computer-vision deep-learning object-detection mxnet

asked Nov 30 '17 at 08:43

damon

vote

1 answer

Strange mxnet behavior in R: results not reproducible

Does mxnet store data/models somewhere outside of R? I keep running into scenarios where the first NN run of the day will produce good results, and every following run (even of the exact same code) will produce NA/NaN for all training…

r neural-network rstudio-server mxnet

asked Nov 18 '17 at 20:24

Garglesoap

vote

1 answer

How do I use an MXNet model in C++?

After I have trained a model, how do I use it with C++? I have tried MXNet incubator-mxnet/example/image-classification/predict-cpp/ and incubator-mxnet/cpp-package/example/.

c++ mxnet

asked Nov 15 '17 at 00:08

king kwan

vote

1 answer

MXNet R package on an Amazon Linux Deep Learning EC2 instance

I'm attempting to setup an Amazon Linux EC2 instance with MXNet and R (and the MXNet r package available as well). Unfortunately this has been a lot harder than I expected. I've attempted to follow the instructions from MXNet using Amazon's deep…

r amazon-web-services amazon-ec2 deep-learning mxnet

asked Nov 14 '17 at 20:19

Taran

vote

1 answer

How to plot the output (bias and weight) of a simple 1 layer model?

I have a very simple model that is the data input to a hidden layer with 2 units that then outputs to an activation layer and then to the softmax layer. mxnet will report the computed bias and weight with something like fullyconnected0_bias -> […

plot mxnet

asked Nov 12 '17 at 15:40

sail0r

vote

1 answer

Word2Vec embedding and CNN on H2O R example

I am wondering if it's possible to provide any r sample code for using word2vec and cnn on text classification in H2O DeepWater R version ? There's very very few documentation on either mexnetR or h2o deep water r I have already used the h2o r…

r nlp word2vec h2o mxnet

asked Nov 03 '17 at 05:23

Weiye Deng

vote

1 answer

simple example of mxnet model parallelism

The simple examples in the Guon tutorial for mxnet are very helpful to those of us who are just getting started with mxnet. As yet, there is not a simple example for model parallelism. I see the model parallelism example code for LSTM, but I am new…

python mxnet

asked Oct 31 '17 at 07:16

John B

vote

2 answers

How to visulize the convolution layer and feature layer in mxnet after cnn was finished trained?

I want to plot or visualize the result of each layers out from a trained CNN with mxnet in R. Like w´those abstract art from what a nn's each layer can see. But I don't know how. Please somebody help me. One way I can think out is to put the…

r layer convolution mxnet visualize

asked Oct 29 '17 at 16:12

jackeikee

vote

1 answer

Issues installing mxnet GPU R package for Amazon deep learning AMI

I am having trouble installing mxnet GPU for R on Amazon deep learning linux AMI. The environment variables are such a mess that it’s a nightmare for any non-expert sys-admin to figure out. Step 1: install the ridiculous amount of missing/broken…

r linux amazon-ec2 mxnet

asked Oct 25 '17 at 22:14

Garglesoap

vote

2 answers

Hyper parameter tuning for multiple Outputs using mxnet in R

I currently try to build MLPs with multiple Outputs. For single Output MLPs I normally use the H2o packge implementation which has a nice random grid search function implemented. Since H2o does not support multiple outputs I switched to the mxnet…

r mxnet hyperparameters

asked Sep 26 '17 at 13:23

Paul

vote

2 answers

mxnet failed to infer type

My mxnet code - which consists of a series of complex connections and slicing raises the following error: Error in operator concat0: [03:03:51] src/operator/./concat-inl.h:211: Not enough information to infer type in Concat. Im not sure how to…

deep-learning mxnet

asked Sep 26 '17 at 07:13

Drew

vote

2 answers

Static graph is fast. Dynamic graph is slow. Is there any specific benchmark demonstrating this?

I've see some benchmark about tensorflow and pytorch. Tensorflow maybe faster but seems not that faster even sometimes slower. Is there any benchmark on specifically testing on static graph and dynamic graph demonstrating that static graph is much…

torch tensorflow pytorch mxnet

asked Sep 20 '17 at 02:18

Saddle Point

3,074
4
23
33

vote

1 answer

How to store MXNet graph visualization as image in a file?

According to this page, MXNet computation graph can be visualized using mx.viz.plot_network(net). But that only works on Jupyter notebook. How do I do it without Jupyter notebook? Is it possible to save the visualization as a image in a file?

mxnet

asked Sep 12 '17 at 20:33

Indhu Bharathi

1,437
1
13
22

vote

2 answers

mxnet training not progressing

Thanks in advance for any help. I am having some issues getting an mxnet model to converge to anything: it seems stuck close to its initial weights. A working example (although I have struggled to get many such models working today). I have tried…

machine-learning neural-network deep-learning mxnet

asked Aug 23 '17 at 21:27

Ats

Prev 1 2 3

…

46 47 Next