Skip to main content
  • Home
  • Development
  • Documentation
  • Donate
  • Operational login
  • Browse the archive

swh logo
SoftwareHeritage
Software
Heritage
Archive
Features
  • Search

  • Downloads

  • Save code now

  • Add forge now

  • Help

swh:1:snp:42a61ec11033680719ca94e3d4e866d9f7fc9d6f
  • Code
  • Branches (1)
  • Releases (0)
    • Branches
    • Releases
    • HEAD
    • refs/heads/master
    No releases to show
  • a6e8e30
  • /
  • main.py
Raw File Download

To reference or cite the objects present in the Software Heritage archive, permalinks based on SoftWare Hash IDentifiers (SWHIDs) must be used.
Select below a type of object currently browsed in order to display its associated SWHID and permalink.

  • content
  • directory
  • revision
  • snapshot
content badge
swh:1:cnt:3db3062b0652e9c5147330144229c7c8440e9769
directory badge
swh:1:dir:a6e8e30292b31e92ecf2a6e99a6a105d97f0bbb5
revision badge
swh:1:rev:914f5ddb06a3853f2f60a09d156702154b084cb3
snapshot badge
swh:1:snp:42a61ec11033680719ca94e3d4e866d9f7fc9d6f

This interface enables to generate software citations, provided that the root directory of browsed objects contains a citation.cff or codemeta.json file.
Select below a type of object currently browsed in order to generate citations for them.

  • content
  • directory
  • revision
  • snapshot
Generate software citation in BibTex format (requires biblatex-software package)
Generating citation ...
Generate software citation in BibTex format (requires biblatex-software package)
Generating citation ...
Generate software citation in BibTex format (requires biblatex-software package)
Generating citation ...
Generate software citation in BibTex format (requires biblatex-software package)
Generating citation ...
Tip revision: 914f5ddb06a3853f2f60a09d156702154b084cb3 authored by HE ZHANG on 27 July 2018, 20:03:31 UTC
change-index
Tip revision: 914f5dd
main.py
import numpy as np
import tensorflow as tf
from MANN import MANN


num_joints  = 27
num_styles  = 6
datapath    = './data' 
savepath    = './training'
num_experts = 8
index_gatingIn = [285, 286, 287, 
                  345, 346, 347, 
                  393, 394, 395, 
                  341, 342, 343,
                  84,  85,  86, 87, 88, 89, 90]

def main():
    rng  = np.random.RandomState(23456)
    sess = tf.Session()
    mann = MANN(num_joints,
                num_styles,
                rng,
                sess,
                datapath, savepath,
                num_experts,
                hidden_size = 512,
                hidden_size_gt = 32, 
                index_gating = index_gatingIn,
                batch_size = 32 , epoch = 150, Te = 10, Tmult =2, 
                learning_rate_ini = 0.0001, weightDecay_ini = 0.0025, keep_prob_ini = 0.7)
    
    mann.build_model()
    mann.train()
    
    
if __name__ =='__main__':
    main()

back to top

Software Heritage — Copyright (C) 2015–2025, The Software Heritage developers. License: GNU AGPLv3+.
The source code of Software Heritage itself is available on our development forge.
The source code files archived by Software Heritage are available under their own copyright and licenses.
Terms of use: Archive access, API— Content policy— Contact— JavaScript license information— Web API