apache /mxnet
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
★ 20,791⑂ 6,666👁 22⑃ 11,124● 9,558▤ 34
+1
Daily
-2
Weekly
-12
Monthly
20,791
stars
6,666
forks
22
watchers
11,124
prs
9,558
issues
34
releases
README
Apache MXNet for Deep Learning
===========================================
Apache MXNet is a deep learning framework designed for both efficiency and flexibility.
It allows you to mix symbolic and imperative programming
to maximize efficiency and productivity.
At its core, MXNet contains a dynamic dependency scheduler that automatically parallelizes both symbolic and imperative operations on the fly.
A graph optimization layer on top of that makes symbolic execution fast and memory efficient.
MXNet is portable and lightweight, scalable to many GPUs and machines.
Apache MXNet is more than a deep learning project. It is a community
on a mission of democratizing AI. It is a collection of blue prints and guidelines
for building deep learning systems, and interesting insights of DL systems for hackers.
Licensed under an Apache-2.0 license.
| Branch | Build Status |
|:-------:|:-------------:|
| master | |
| v1.x | |
Features
--------
NumPy-like programming interface, and is integrated with the new, easy-to-use Gluon 2.0 interface. NumPy users can easily adopt MXNet and start in deep learning.
Automatic hybridization provides imperative programming with the performance of traditional symbolic programming.
Lightweight, memory-efficient, and portable to smart devices through native cross-compilation support on ARM, and through ecosystem projects such as TVM, TensorRT, OpenVINO.
Scales up to multi GPUs and distributed setting with auto parallelism through ps-lite, Horovod, and BytePS.
Extensible backend that supports full customization, allowing integration with custom accelerator libraries and in-house hardware without the need to maintain a fork.
Support for Python, Java, C++, R, Scala, Clojure, Go, Javascript, Perl, and Julia.
Cloud-friendly and directly compatible with AWS and Azure.
Contents
--------
Installation
Tutorials
Ecosystem
API Documentation
Examples
Stay Connected
Social Media
What's New
----------
1.9.1 Release - MXNet 1.9.1 Release.
1.8.0 Release - MXNet 1.8.0 Release.
1.7.0 Release - MXNet 1.7.0 Release.
1.6.0 Release - MXNet 1.6.0 Release.
1.5.1 Release - MXNet 1.5.1 Patch Release.
1.5.0 Release - MXNet 1.5.0 Release.
1.4.1 Release - MXNet 1.4.1 Patch Release.
1.4.0 Release - MXNet 1.4.0 Release.
1.3.1 Release - MXNet 1.3.1 Patch Release.
1.3.0 Release - MXNet 1.3.0 Release.
1.2.0 Release - MXNet 1.2.0 Release.
1.1.0 Release - MXNet 1.1.0 Release.
1.0.0 Release - MXNet 1.0.0 Release.
0.12.1 Release - MXNet 0.12.1 Patch Release.
0.12.0 Release - MXNet 0.12.0 Release.
0.11.0 Release - MXNet 0.11.0 Release.
Apache Incubator - We are now an Apache Incubator project.
0.10.0 Release - MXNet 0.10.0 Release.
0.9.3 Release - First 0.9 official release.
0.9.1 Release (NNVM refactor) - NNVM branch is merged into master now. An official release will be made soon.
0.8.0 Release
Ecosystem News
oneDNN for Faster CPU Performance
MXNet Memory Monger, Training DeeperTop issues
#17783[RFC] MXNet 2.0 JVM Language development55 comments · 2020-03-06#10002General support of OPs for second-order gradient55 comments · 2018-03-06#18800[RFC] v1.8.0 release54 comments · 2020-07-27#621Support for other Device Types, OpenCL AMD GPU43 comments · 2015-11-18#19897能否详细写一下最新的mxnet GPU如何在win10下编译?Can you write the latest MXNET GPU in detail how to compile under Win10?42 comments · 2021-02-15#19048[BUG] config for windows?41 comments · 2020-08-30#17097[RFC][mxnet 2.0][item 10.1] MXNet Imperative Op Invocation Overhead38 comments · 2019-12-17#2986[call for contribution] Improving CPU performance37 comments · 2016-08-10
Discussions
#21218mxnet.base.MXNetError: [08:13:05] src/ndarray/ndarray.cc:1137: Check failed: to.IsDefaultData()0 comments · 2023-09-21#21211mx.image.imdecode to numpy causes the speed to slow down0 comments · 2023-07-26#21201sorting a tensor with the indices from argsort - is there a symbol operator?1 comments · 2023-05-12#21200Embedding - error when using sparse grads - what else needs to be enabled/configured to use this?0 comments · 2023-05-12#21194Cannot reshape array of size 1 into shape [1,10] Please Help0 comments · 2023-04-26#21192Failed mxnet unit tests0 comments · 2023-04-05#21177mxnet - wrong dates ploted0 comments · 2023-01-27#21174Installing MXNet Perl Bindings - mxnet_wrap.cxx 'c_api.h' file not found2 comments · 2023-01-13
Latest release
Apache MXNet (incubating) 1.9.1 patch release 1.9.1 2022-05-10Apache MXNet (incubating) 1.9.1 is a maintenance release incorporating important bug fixes and performance improvements. All users of Apache MXNet (incubating) 1.9.0 are advised to upgrade. You can install Apache MXNet (incubating) 1.9.1 at the usual place. Please review these Release Notes to learn the bug fixes. Bug-fixes - Upgrade numpy to <1.20.0 to avoid security vulnerabilities affecting numpy<1.19.1 (20940) - quantized elemwise mul changed out type to float (20926) - Avoid modifying loaded library map while iterating in lib_close() (20941) (20944) - Fixed issue with batchnorm