Paquet : python3-keras (2.3.1+dfsg-3)

[ Paquet source : keras  ]

deep learning framework running on Theano or TensorFlow

Keras is a Python library for machine learning based on deep (multi- layered) artificial neural networks (DNN), which follows a minimalistic and modular design with a focus on fast experimentation.

Features of DNNs like neural layers, cost functions, optimizers, initialization schemes, activation functions and regularization schemes are available in Keras a standalone modules which can be plugged together as wanted to create sequence models or more complex architectures. Keras supports convolutions neural networks (CNN, used for image recognition resp. classification) and recurrent neural networks (RNN, suitable for sequence analysis like in natural language processing).

It runs as an abstraction layer on the top of Theano (math expression compiler) by default, which makes it possible to accelerate the computations by using (GP)GPU devices. Alternatively, Keras could run on Google's TensorFlow (not yet available in Debian).

Autres paquets associés à python3-keras

• dep: python3

  langage orienté objet interactif de haut niveau – version par défaut de Python 3

• dep: python3-h5py

  general-purpose Python interface to hdf5

• dep: python3-keras-applications (>= 1.0.8)

  popular models and pre-trained weights for the Keras deep learning framework

• dep: python3-keras-preprocessing (>= 1.1.0)

  data preprocessing module for the Keras deep learning framework

• dep: python3-numpy

  gestion rapide des tableaux avec le langage Python 3

• dep: python3-scipy

  outils scientifiques pour Python 3

• dep: python3-six (>= 1.9.0)

  bibliothèque de compatibilité Python⋅2 et⋅3 –⋅interface Python⋅3

• dep: python3-theano

  CPU/GPU math expression compiler for Python 3

• dep: python3-yaml

  analyseur et générateur de code YAML pour Python3

Télécharger python3-keras

Télécharger pour toutes les architectures proposées

Architecture	Taille du paquet	Espace occupé une fois installé	Fichiers
all	231,4 ko	1 764,0 ko	[liste des fichiers]