Пакет: python3-keras (2.3.1+dfsg2-1)

[ Источник: 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).

Другие пакеты, относящиеся к python3-keras

• dep: python3

  интерактивный высокоуровневый объектно-ориентированный язык (версия python3 по умолчанию)

• dep: python3-h5py

  general-purpose Python interface to hdf5

• dep: python3-h5py-serial

  general-purpose Python interface to hdf5 (Python 3 serial)

• 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

  Fast array facility to the Python language (Python 3)

• dep: python3-scipy

  scientific tools for Python 3

• dep: python3-six (>= 1.9.0)

  Python 2 and 3 compatibility library

• dep: python3-theano

  Пакет недоступен

• dep: python3-yaml

  YAML parser and emitter for Python3

Загрузка python3-keras

Загрузить для всех доступных архитектур

Архитектура	Размер пакета	В установленном виде	Файлы
all	231,6 Кб	1 763,0 Кб	[список файлов]