Apache MXNet (incubating) Documents¶
Note
This is a preview of the new website for Apache MXNet (incubating) that will eventually replace https://mxnet.apache.org. Currently this site focuses on the Python and R frontends with a subset of tutorials. It is under fast development and we welcome contributions. Check What’s New for a summary about what is changed and also look at the roadmap for upcoming changes.
Apache MXNet (incubating) aims to be a flexible and efficient library for deep learning. It’s designed for both researchers to quickly prototype ideas as well as engineers to apply deep learning technologies to products.
Install¶
Platform: Local Cloud Devices
Device: Raspberry Pi Jetson
How to install MXNet on a Raspberry Pi 3.
How to install MXNet on a Jetson TX.
Provider: Alibaba AWS Google Cloud Microsoft Azure Oracle Cloud
Installation Guides:
AWS Deep Learning AMI: preinstalled Conda environments for Python 2 or 3 with MXNet, CUDA, cuDNN, MKL-DNN, and AWS Elastic Inference
Amazon SageMaker: managed training and deployment of MXNet models
Dynamic Training on AWS: experimental manual EC2 setup or semi-automated CloudFormation setup
OS: Linux macOS Windows
Package: Pip Docker
Backend: Native CUDA MKL-DNN CUDA + MKL-DNN
Prerequisites:
Requires docker and Docker can be used by a non-root user.
nvidia-docker is required to run on Nvidia GPUs.
Requires pip >= 9.. Both Python 2 and Python 3 are supported.
Hint: append the flag
--preat the end of the command will install the nightly build.
Hint: MKL-DNN is already included in the MXNet binary, so you don’t need to install it.
For detailed information on MKL and MKL-DNN, refer to the MKLDNN_README.
Command:
pip install mxnet
# Here we assume CUDA 9.2 is installed. You can change the number
# according to your own CUDA version.
pip install mxnet-cu92
pip install mxnet-mkl
# Here we assume CUDA 9.2 is installed. You can change the number
# according to your own CUDA version.
pip install mxnet-cu92mkl
docker pull mxnet/python
docker pull mxnet/python:gpu
docker pull mxnet/python:1.3.0_cpu_mkl
docker pull mxnet/python:1.3.0_gpu_cu90_mkl_py3
Check Install for more installation instructions and options.
Documents¶
Guides for using MXNet.
API reference to all MXNet classes and methods.
Ecosystem¶
An interactive book to learn deep learning for students and engineers.
A deep learning toolkit for computer vision.
A deep learning toolkit for natural language processing.
A seq2seq toolkit with a focus on Neural Machine Translation.
Keras with Apache MXNet as its backend.
Community¶
Report bugs, request features, discuss issues, and more.
Comment and discuss this site to help us improve the documentation quality.
Browse and join the discussion on deep learning with MXNet.
