Balík: python3-keras (2.2.4-1)
Odkazy pre python3-keras
Zdroje Debian:
Stiahnuť zdrojový balík keras:
Správcovia:
Externé zdroje:
- Domovská stránka [keras.io]
Podobné balíky:
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).
Ostatné balíky súvisiace s balíkom python3-keras
|
|
|
|
-
- dep: python3
- interaktívny vysokoúrovňový objektovo orientovaný jazyk (predvolená verzia python3)
-
- dep: python3-h5py
- rozhranie k hdf5 na všeobecné účely pre Python 3
-
- dep: python3-keras-applications
- popular models and pre-trained weights for the Keras deep learning framework
-
- dep: python3-keras-preprocessing
- data preprocessing module for the Keras deep learning framework
-
- dep: python3-numpy
- schopnosti rýchlych polí do jazyka Python 3
-
- dep: python3-scipy
- vedecké nástroje pre Python 3
-
- dep: python3-six (>= 1.9.0)
- knižnica na kompatibilitu Pythonu 2 a 3 (rozhranie Python 3)
-
- dep: python3-theano
- CPU/GPU math expression compiler for Python 3
-
- dep: python3-yaml
- spracovanie a tvorbu YAML v jazyku Python 3
Stiahnuť python3-keras
Architektúra | Veľkosť balíka | Nainštalovaná veľkosť | Súbory |
---|---|---|---|
all | 197.3 kB | 1,502.0 kB | [zoznam súborov] |