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
0 answers

loss decreasing but accuracy stays the same for 3D convnet

I am trying to train a 3D convnet with 3D spatial data using mxnet. When I run the program the loss decreases normally over epochs but the training accuracy and the test accuracy is staying exactly the same. I am very new to neural networks and I…
accAscrub
  • 609
  • 1
  • 6
  • 11
0
votes
1 answer

How to get 3D convnet to classify spatial data?

I am trying to train a 3D convolutional neural network using 3D spatial data. The network trains ok but when I check its accuracy I get the following error: ValueError: Shape of labels 64 does not match shape of predictions 1. I do not know why the…
accAscrub
  • 609
  • 1
  • 6
  • 11
0
votes
0 answers

mxnet-cpp operator lookup failing

In c++ mx: #include namespace mx { using namespace mxnet::cpp; } int main(int argc, char *argv[]) { auto data = mx::Symbol::Variable("input"); mx::Symbol conv_w("conv1_w"), conv_b("conv1_b"); auto a =…
iamacomputer
  • 518
  • 3
  • 14
0
votes
1 answer

Sample code for model-parallel and pipelined training in TensorFlow

Naive model-partitioning across several GPUs results in the workload moving from GPU to GPU during the forward and backward pass. At any instant, one GPU is busy. Here's the naive version. with tf.device('/gpu:0'): model.add(Conv2D(32,…
auro
  • 1,079
  • 1
  • 10
  • 22
0
votes
1 answer

Import MXNet file in Keras/Tensorflow

I am having trouble finding the answer to this. I have an MXNet file in the form of: model.json and model.params. What is the cleanest way to load the network into a Keras installation with TensorFlow backend?
aaaaaaaardvark
  • 11
  • 2
0
votes
1 answer

How to process data for 3d convolutional neural network?

I have a collection of 11*11*21 3D data that I want to use a 3D convnet to classify. By using gluon's dataloader with a batch size of 64, my input tensor for the network was (64L, 11L, 11L, 21L). When I tried to run the program I got the following…
accAscrub
  • 609
  • 1
  • 6
  • 11
0
votes
1 answer

Using numpy.ndarray type (multilabel) for labels in Sagemaker RecordIO format?

I am trying to write a numpy.ndarray as the labels for Amazon Sagemaker's conversion tool: write_numpy_to_dense_tensor(). It converts a numpy array of features and labels to a RecordIO for better use of Sagemaker algorithms. However, if I try to…
Tom
  • 554
  • 5
  • 22
0
votes
1 answer

Why Convolution function in MXnet have a kernel parameter

I am new of mxnet, in the official doc, the generation of a convolution layer could be conv = nd.Convolution(data=data, weight=W, bias=b, kernel=(3,3), num_filter=10) But it is required that the weight parameter needs to take a 4-D tensor W =…
Litchy
  • 355
  • 1
  • 4
  • 18
0
votes
1 answer

How to combine dataset with mxnet?

I have two separate folders containing 3D arrays (data), each folder contains files of the same classification. I used mxnet.gluon.data.ArrayDataset() create datasets for each label respectively. Is there a way to combine these two datasets into the…
accAscrub
  • 609
  • 1
  • 6
  • 11
0
votes
1 answer

MXNet: sequence length in LSTM in a non-sequence data (R)

My data are not timeseries, but it has sequential properties. Consider one sample: data1 = matrix(rnorm(10, 0, 1), nrow = 1) label1 = rnorm(1, 0, 1) label1 is a function of the data1, but the data matrix is not a timeseries. I suppose that label…
Alexey Burnakov
  • 259
  • 2
  • 14
0
votes
1 answer

mxnet: save list of tuples of arrays to file

I'm using mxnet to do deep reinforcement learning. I have a simple generator that yields observations from a random walk through a game (from openai gym): import mxnet as mx from mxnet import * from mxnet.ndarray import * import gym def…
matan tsuberi
  • 145
  • 1
  • 12
0
votes
1 answer

How to input additional data into the network when high-level APIs are being used in MXNet

I am studying MXNet framework and I need to input a matrix into the network during every iteration. The matrix is stored in external memory, it is not the training data and it is updated by the output of the network at the end of each iteration.…
HoiM
  • 81
  • 6
0
votes
1 answer

Get hidden layer outputs

I make a densenet network from gluon.vision densenet = vision.densenet121(pretrained=True, ctx=mx.cpu()) I want to get the outputs of each convolutionnal layer (after a prediction), to plot them afterwards (features maps). I can't do…
Jérémy Blain
  • 249
  • 2
  • 14
0
votes
1 answer

Error in prediction script using CNN model for text classification

I am try to write prediction part of script for the tutorial: https://mxnet.incubator.apache.org/tutorials/nlp/cnn.html import mxnet as mx from collections import Counter import os import re import threading import sys import itertools import…
Alex
  • 45
  • 4
0
votes
1 answer

How to check deep embedded clustering on new data?

I'm using DEC from mxnet (https://github.com/apache/incubator-mxnet/tree/master/example/deep-embedded-clustering) While it defaults to run on the MNIST, I have changed the datasource to several hundreds of documents (which should be perfectly fine,…
David Niki
  • 1,092
  • 1
  • 11
  • 14
1 2 3
…
46 47