lua-torch-nn 0~20171002-g8726825+dfsg-4 source package in Ubuntu

Changelog

lua-torch-nn (0~20171002-g8726825+dfsg-4) unstable; urgency=medium

  * Add new include path due to lua-torch-torch7's header path move.
    (Closes: #908657)
  * Bump Standards-Version to 4.2.1 (no change).
  * Modify test.lua to adapt to lua-moses' API change. (Closes: #907791)
    + debian/patches/lua-moses-2.0.0.patch
  * Require lua-moses (>= 2.0.0~) as both Build-Depends and Depends.

 -- Mo Zhou <email address hidden>  Wed, 12 Sep 2018 10:09:08 +0000

Upload details

Uploaded by:
Debian Science Team on 2018-09-12
Uploaded to:
Sid
Original maintainer:
Debian Science Team
Architectures:
all amd64 arm64 armel armhf ppc64el kfreebsd-amd64 i386
Section:
misc
Urgency:
Medium Urgency

See full publishing history Publishing

Series Pocket Published Component Section
Eoan release on 2019-04-18 universe misc
Disco release on 2018-11-11 universe misc

Downloads

File Size SHA-256 Checksum
lua-torch-nn_0~20171002-g8726825+dfsg-4.dsc 2.4 KiB 913b37e3036ba7483451f31fa2becf07acc0eb6651e9e8ee120eff8cb0ab6311
lua-torch-nn_0~20171002-g8726825+dfsg.orig.tar.xz 447.0 KiB 83e1f80f1826727a50f571f493b4b77369804131cd09aa1c8a6cc256945414f1
lua-torch-nn_0~20171002-g8726825+dfsg-4.debian.tar.xz 8.2 KiB 15a9c333923ee3ccc3760b6aac18cd5da385321012e1517203d809f6c0476f0b

No changes file available.

Binary packages built by this source

libtorch-thnn: libTHNN.so of Neural Network Package for Torch Framework

 This package provides an easy and modular way to build and train
 simple or complex neural networks using Torch Framework.
 .
 This package contains libTHNN.so , backend library for lua-torch-nn.

libtorch-thnn-dbgsym: debug symbols for libtorch-thnn
libtorch-thnn-dev: libTHNN.so of Neural Network Package for Torch Framework (dev)

 This package provides an easy and modular way to build and train
 simple or complex neural networks using Torch Framework.
 .
 This package contains headers for libTHNN.so .

lua-torch-nn: Neural Network Package for Torch Framework

 This package provides an easy and modular way to build and train
 simple or complex neural networks using Torch Framework:
 .
  * Modules are the bricks used to build neural networks.
    Each are themselves neural networks, but can be combined with
    other networks using containers to create complex neural networks:
 .
    + Module: abstract class inherited by all modules.
    + Containers: container classes.
    + Transfer functions: non-linear functions.
    + Simple layers: simple network layer like `Linear`.
    + Table layers: layers for manipulating `table`s.
    + Convolution layers: several kinds of convolutions.
 .
  * Criterions compute a gradient according to a given loss function
    given an input and a target:
 .
    + Criterions: a list of all criterions.
    + `MSECriterion`: the Mean Squared Error criterion used for regression;
    + `ClassNLLCriterion`: the Negative Log Likelihood criterion used for
      classification.
 .
  * Additional documentation:
 .
   + Overview of the package essentials including modules, containers
     and training.
   + Training: how to train a neural network using optim.
   + Testing: how to test your modules.
   + Experimental Modules: a package containing experimental modules and
     criteria.
 .
 This package is a core part of the Torch Framework.