This is the Linux app named Model Search whose latest release can be downloaded as model_searchsourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named Model Search with OnWorks for free.
Suivez ces instructions pour exécuter cette application :
- 1. Téléchargé cette application sur votre PC.
- 2. Entrez dans notre gestionnaire de fichiers https://www.onworks.net/myfiles.php?username=XXXXX avec le nom d'utilisateur que vous voulez.
- 3. Téléchargez cette application dans ce gestionnaire de fichiers.
- 4. Démarrez l'émulateur en ligne OnWorks Linux ou Windows en ligne ou l'émulateur en ligne MACOS à partir de ce site Web.
- 5. Depuis le système d'exploitation OnWorks Linux que vous venez de démarrer, accédez à notre gestionnaire de fichiers https://www.onworks.net/myfiles.php?username=XXXXX avec le nom d'utilisateur que vous souhaitez.
- 6. Téléchargez l'application, installez-la et exécutez-la.
CAPTURES D'ÉCRAN
Ad
Recherche de modèle
DESCRIPTION
Model Search is an AutoML research system for discovering neural network architectures with minimal human intervention. Instead of hand-crafting models, you define a search space and objectives, then the system explores candidate architectures using controllers and population-based strategies. It supports multiple tasks (such as vision or text) by letting you express reusable building blocks—layers, cells, and topologies—that the search can recombine. Training, evaluation, and promotion of candidates are orchestrated automatically, with strong emphasis on reproducibility and fair comparisons. The framework logs trials, metrics, and artifacts so you can analyze what the search learned and why certain designs dominate. It’s intended as a platform for method development as much as for model discovery.
Comment ça marche
- Declarative search spaces for layers, cells, and connections
- Population-based training with promotion, mutation, and exploitation
- Multi-task support with pluggable input pipelines and heads
- Automated trial management, checkpointing, and early stopping
- Rich metric logging and artifact tracking for post-hoc analysis
- Extensible controllers to test new NAS algorithms
Langage de programmation
Python
Catégories
This is an application that can also be fetched from https://sourceforge.net/projects/model-search.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
