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
1
vote
1 answer

MXNet backward shape inconsistent

After upgrading to MXNet 0.11.0 I get strange errors in my old code: Working with the boston housing dataset from scikit-learn: data = mx.sym.Variable("data") y = mx.sym.Variable("output_label") fc =…
Dhruv Madeka
  • 31
  • 1
1
vote
1 answer

Matching PyTorch w/ CNTK (VGG on CIFAR)

I am trying to understand how PyTorch works and want to replicate a simple CNN training on CIFAR. The CNTK script gets to 0.76 accuracy after 168 seconds of training (10 epochs), which is similar to my MXNet script (0.75 accuracy after 153…
Ilia
  • 69
  • 4
1
vote
1 answer

example for custom iterator not working

I am following the description and example for creating a custom iterator as described here: http://mxnet.io/tutorials/basic/data.html The following code produces a ValueError: mod.fit(data_iter, num_epoch=5) ValueError: Shape of labels 0 does not…
user224637
  • 173
  • 2
  • 12
1
vote
1 answer

LSTM to predict sine wave

Here I would like to generate a tutorial usage of LSTM in MxNet, with the example for Tensorflow. (location at https://github.com/mouradmourafiq/tensorflow-lstm-regression/blob/master/lstm_sin.ipynb" Here is my major code import mxnet as mx import…
user2189731
  • 558
  • 8
  • 15
1
vote
1 answer

BoundsError in Julia MXNet when using small batch size

I'm trying to reproduce some Python MXNet code in Julia 0.6.0, and I'm getting a BoundsError if I try to use a batch size that is smaller than the dimension of the output. If I use a larger batch size in a toy example, things work properly and the…
Robert Crandall
  • 11
  • 1
1
vote
1 answer

Gradient descent using MXNet NDArray

I'm trying to use MXNet to do some constrained optimization that isn't backpropogation in a feedforward network, but involves similar computations, products of large arrays, some gradient descent, etc... For example, to minimize the trace of M-2*Id…
John Terilla
  • 11
  • 3
1
vote
1 answer

MxNet: label_shapes don't match names specified by label_names

I wrote a script to do the classification of a single input image using a model I trained with MxNet. To classify the incoming image I feedforward them in through network. In short here is what I am doing: symbol, arg_params, aux_params =…
Pierre-Antoine
  • 7,939
  • 6
  • 28
  • 36
1
vote
1 answer

shape mismatch using RNN in MXNet - R

I am trying to use a RNN in MXNet to do a classification. My data roughly looks like the matrices m0 and m1 I created. m0 represents e.g. energy consumption of a device over time, while m1 is my label to tell how the device is to be classified (e.g.…
fjba
  • 11
  • 3
1
vote
1 answer

mxnet (mshadow) getting the shape of a tensor

I'm a newbie in mshadow, I can not understand why I got those outpus from the following code snippet: TensorContainer lhs(Shape2(2, 3)); lhs = 1.0; printf("%u %u\n", lhs.size(0), lhs.size(1)); printf("%u %u\n", lhs[0].shape_[0],…
ROBOT AI
  • 1,217
  • 3
  • 16
  • 27
1
vote
1 answer

Is conditional computing possible with Tensorflow?

I am working on a conditional computing framework using MxNet. Assume that we have N samples in our minibatch. I need to execute such kind of operations in my computational graph, using pseudocode: x = graph.Variable("x") y =…
Ufuk Can Bicici
  • 3,589
  • 4
  • 28
  • 57
1
vote
1 answer

Mxnet Bind error of lro_labels and data for image regression

I use mxnet to do image regression(4 labels) by fine-tuning resnet50. I changed SoftmaxOutput with LinearRegressionOutput in symbol I changed image label into a number I used metric=mx.metric.MSE() instead of training acc. So the symbol is like in…
David Ding
  • 680
  • 3
  • 9
  • 19
1
vote
1 answer

MXNetR Not enough information to get shape

I am implementing a neural network in MXNetR. I attempted to customize my loss function to compute the correlation between my output vector and the targeting vector. Below is my code: Below is my code: # Generate testing data train.x = matrix(data =…
nnguyen24
  • 21
  • 1
  • 4
1
vote
2 answers

attributeError:'module' object has no attribute 'MXIndexedRecordIO'

I have used im2rec.py to convert "caltech101 images" into record io format: I have created "caltech.lst" succesfully using os.system('python %s/tools/im2rec.py --list=1 --recursive=1 --shuffle=1 data/caltech…
user3824903
  • 11
  • 3
1
vote
1 answer

How can we create mixture density networks with MXNet?

I am evaluating MXNet in R and I would like to model mixture density netowrks. An example with Tensorflow, Keras and Edward can be found here: http://cbonnett.github.io/MDN_EDWARD_KERAS_TF.html The example shown is a mixture of Normal Distributions.…
user7993865
  • 11
  • 2
1
vote
0 answers

ld could not find .so even with LD_LIBRARY_PATH AND LD_RUN_PATH set

When I compile mxnet, it said /usr/bin/ld: cannot find -liomp5 Then I try ld -liomp5 ld: cannot find -liomp5 but ld -Lpathlibiomp5 -liomp5 said "ld: warning: cannot find entry symbol _start; not setting start address" I have set the following…
sunxd
  • 743
  • 1
  • 9
  • 24
1 2 3
…
46 47