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

Queries regarding Symbolic API in MXNet in Julia

I am struggling to understand the symbolic API nuances of MXNet in Julia. I saw an example in MXNet documentation which has the following line: act1 = mx.Activation(data = fc1, name=:relu1, act_type=:relu) Why is act_type assigned the symbol…
Abhishek Kishore
  • 340
  • 2
  • 13
0
votes
1 answer

On the page http://mxnet.io/tutorials/python/mnist.html# the weight matrix dimension is incorrect

Under Multilayer Perceptron subsection, the documentation says that weight matrix has a dimension of mk.However, I think it should be km because the output layer-Y has the dimension of n*k. Is my understanding correct?
Abhishek Kishore
  • 340
  • 2
  • 13
0
votes
1 answer

How does a module/optimizer choose which symbols to optimize?

I realize I can make my own module/optimizer to do this, but can existing mxnet modules be told to optimize only a subset of variables? Along those same lines, how does a module determine which symbols to optimize as it is? For example, unlike…
James
  • 85
  • 5
0
votes
1 answer

mxnet: multiple dropout layers with shared mask

I'd like to reproduce a recurrent neural network where each time layer is followed by a dropout layer, and these dropout layers share their masks. This structure was described in, among others, A Theoretically Grounded Application of Dropout in…
liori
  • 40,917
  • 13
  • 78
  • 105
0
votes
1 answer

Errors using onehot_encode incorrect input format?

I'm trying to use the mx.nd.onehot_encode function, which should be straightforward, but I'm getting errors that are difficult to parse. Here is the example usage I'm trying. m0 = mx.nd.zeros(15) mx.nd.onehot_encode(mx.nd.array([0]), m0) I expect…
James
  • 85
  • 5
0
votes
1 answer

The GANs gaussian simulator doesn't converge.

I try to reimplement the Gaussian simulator described in the GANs paper with mxnet. But there are two problems in my code. First, the model doesn't converge very well, even after I try to set a learning rate scheduler. This is how it looks like…
liuwaiting
  • 11
  • 1
0
votes
1 answer

mxnet: how to retrieve the number of example from the DataIter object?

After using the mx.io.ImageRecordIter() to load my training examples, is there a way to retrieve the total number of examples from the returned DataIter object ? Many thanks,
HALMTL
  • 39
  • 3
0
votes
1 answer

Error in mx.sym.Reshape() from http://mxnet.io/tutorials/nlp/cnn.html

I'm trying to follow the Text Classification Tutorial on http://mxnet.io/tutorials/nlp/cnn.html Until I call the function: conv_input = mx.sym.Reshape(data=embed_layer, target_shape=(batch_size, 1, sentence_size, num_embed)) everything goes well.…
hag o hi
  • 117
  • 1
  • 1
  • 9
0
votes
2 answers

Using mxnet pre-trained image classification model in R

Running the tutorial at the link below, I get the error below when I get to the step below. No errors before this point. http://mxnet.io/tutorials/r/classifyRealImageWithPretrainedModel.html prob <- predict(model, X=normed) [19:01:35]…
Chris Hamson
  • 219
  • 1
  • 2
  • 6
0
votes
1 answer

MXNET build model error on r

When I try to use mxnet to build a feedforward model it appeared the following error: Error in mx.io.internal.arrayiter(as.array(data), as.array(label), unif.rnds, : basic_string::_M_replace_aux I follow the R regression example on mxnet…
Chao Liu
  • 1
0
votes
1 answer

How can I make a predict with a lstm-ctc checkpoint in mxnet?

I following example/warpctc/lstm_ocr.py to training a model. Now I had saved a checkpoint mymodel-0100.params and mymodel-symbol.json. So, How can I make a predict with this checkpoint use only one image? I had tired to use Predictor interface, code…
Bob Liu
  • 166
  • 1
  • 9
0
votes
2 answers

Where to download MXNet pre-trained model file final-0000.params

I followed the tutorial of object detection in mxnet, http://mxnet.io/tutorials/computer_vision/detection.html but I don't download the pretrained network and place the extracted file final-0000.params. Where place I can find the file to download in…
Y.Weng
  • 33
  • 5
0
votes
1 answer

Time Series Analysis using Convolutional Neural Network of mxnet

I am trying to analyze a time series in R using convolutional neural network function provided in the mxnet package. Please let me know 1) What should be the value of num.filter in mx.symbol.Convolution? 2) What changes are to be done in the code…
Sohom Ghosh
  • 1
  • 3
0
votes
1 answer

Mxnet Amalgamation compilation issue

Has anyone tried Mxnet amalgamation for android recently. I am getting stuck at the below issue. Have tried setting jni path etc, but to no avail python ./amalgamation.py mxnet_predict0.d mxnet_predict0.cc mxnet_predict-all.cc 0 Not processed:…
user3550694
  • 81
  • 7
0
votes
0 answers

Trouble installing mxnet on OSX Capitan

I am trying to compile mxnet (http://mxnet.readthedocs.org/en/latest/index.html) on OSX Capitan from https://github.com/dmlc/mxnet. After following the installation instructions and verifying that all dependencies are in place I am encountering the…
aaron
  • 6,339
  • 12
  • 54
  • 80
1 2 3
…
46 47