Пакет: keras-doc (2.2.4-1)

[ Източник: keras  ]

CPU/GPU math expression compiler for Python (docs)

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).

This package contains the documentation for Keras.

Други пакети, свързани с keras-doc

• dep: fonts-font-awesome (>= 5.0.10+really4.7.0~dfsg-1)

  iconic font designed for use with Twitter Bootstrap

• dep: libjs-highlight.js

  JavaScript library for syntax highlighting

• dep: libjs-jquery (>= 3.2.1-1)

  JavaScript library for dynamic web applications

• dep: libjs-lunr (>= 2.3.5~dfsg-6)

  simple full-text search - web browsers

• dep: libjs-modernizr (>= 2.6.2+ds1-3)

  JavaScript library to detect HTML5 and CSS3 features in the user's browser

• dep: mkdocs (>= 1.0.4+dfsg-1)

  Static site generator geared towards building project documentation

• dep: sphinx-rtd-theme-common (>= 0.4.2+dfsg-1)

  sphinx theme from readthedocs.org (common files)

• sug: python3-keras

  deep learning framework running on Theano or TensorFlow

Изтегляне на keras-doc

Изтегляне за всички налични архитектури

Архитектура	Големина на пакета	Големина след инсталиране	Файлове
all	315,4 кБ	2 271,0 кБ	[списък на файловете]