marian-nmt/marian
1
1
Fork 0
mirror of https://github.com/marian-nmt/marian.git synced 2024-08-17 10:10:26 +03:00
Code Issues Packages Projects Releases Wiki Activity
Fast Neural Machine Translation in C++
661 Commits 41 Branches 10 Tags 44 MiB
C++ 85.4%
Cuda 8.3%
CMake 3.3%
Python 1.8%
Batchfile 0.4%
Other 0.7%
5062f7b230
Go to file
Marcin Junczys-Dowmunt 5062f7b230 dropout over source and target words
2017-02-26 23:22:46 +00:00
doc Added more references 2016-10-06 10:25:53 -05:00
marian consistent UNK and EOS. Compile error on clang 2017-02-06 20:58:29 +00:00
src dropout over source and target words 2017-02-26 23:22:46 +00:00
.gitignore Revert "more clean-up" 2017-02-02 15:39:48 +00:00
CMakeLists.txt scaling dropout across rnn time steps and layers 2017-02-26 20:24:17 +00:00
Doxyfile.in Exclude 3rd party code from generated docs 2016-10-03 12:31:54 -05:00
LICENSE.md Update LICENSE.md 2016-09-30 00:13:14 +01:00
README.md Change Jenkins server from fatboy to uedin's vali 2017-02-09 18:10:02 +00:00

README.md

Marian

Join the chat at https://gitter.im/amunmt/marian Build Status

Google group for commit messages: https://groups.google.com/forum/#!forum/mariannmt

A C++ gpu-specific parallel automatic differentiation library with operator overloading.

In honour of Marian Rejewski, a Polish mathematician and cryptologist.

Installation

Requirements:

  • g++ with c++11
  • CUDA
  • Boost (>= 1.56)

Compilation with cmake > 3.5:

mkdir build
cd build
cmake ..
make -j