NGC Library
Project description
Neural Graph Consensus library (ngclib)
This is a library containing the implementation of various basic blocks in the NGC project
- the base NGC class as well as various implementations (NGC-V1, NGC-Ensemble)
- iterative trainer for the ngc (sequential, parallel)
- semisupervised generic pseudolabels algorithm
- analysis of an ngcdir for training and data status
- nodes importer -- required to import a repository of nodes containing the basic definition of all nodes and edges
Projects using this library:
- Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus (accepted at AAAI2021)
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ngclib-0.5.tar.gz
(36.1 kB
view details)
File details
Details for the file ngclib-0.5.tar.gz.
File metadata
- Download URL: ngclib-0.5.tar.gz
- Upload date:
- Size: 36.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.8.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 3cedf86414c6e3a537c72954d717b5c3c75b2405d912d987e8731fb3d574d3e7 |
|
| MD5 | 805b420176a0aed5e0ba0158e55ae4cf |
|
| BLAKE2b-256 | ac63a3eb3c84602a2979a83474348bc98b1457c6c1d9c3b5c98366dc544fbcbd |
