toutes les options
buster  ]
[ Paquet source : lua-torch-optim  ]

Paquet : lua-torch-optim (0~20171127-ga5ceed7-1)

Liens pour lua-torch-optim

Screenshot

Ressources Debian :

Télécharger le paquet source lua-torch-optim :

Responsables :

Ressources externes :

Paquets similaires :

Numeric Optimization Package for Torch Framework

This package contains several optimization routines and a logger for Torch.

The following algorithms are provided:

 * Stochastic Gradient Descent
 * Averaged Stochastic Gradient Descent
 * L-BFGS
 * Congugate Gradients
 * AdaDelta
 * AdaGrad
 * Adam
 * AdaMax
 * FISTA with backtracking line search
 * Nesterov's Accelerated Gradient method
 * RMSprop
 * Rprop
 * CMAES
All these algorithms are designed to support batch optimization as well as stochastic optimization. It's up to the user to construct an objective function that represents the batch, mini-batch, or single sample on which to evaluate the objective.

This package provides also logging and live plotting capabilities via the `optim.Logger()` function. Live logging is essential to monitor the network accuracy and cost function during training and testing, for spotting under- and over-fitting, for early stopping or just for monitoring the health of the current optimisation task.

Autres paquets associés à lua-torch-optim

  • dépendances
  • recommandations
  • suggestions
  • enhances

Télécharger lua-torch-optim

Télécharger pour toutes les architectures proposées
Architecture Taille du paquet Espace occupé une fois installé Fichiers
all 210,0 ko350,0 ko [liste des fichiers]