Debian Codegraph @

debian/control

raw
1 Source: keras-preprocessing
2 Maintainer: Debian Science Maintainers <[email protected]>
3 Uploaders:
4 Stephen Sinclair <[email protected]>,
5 Section: science
6 Build-Depends:
7 debhelper-compat (= 14),
8 dh-sequence-python3,
9 python3-all,
10 python3-numpy,
11 python3-setuptools,
12 Standards-Version: 4.7.4
13 Vcs-Browser: https://salsa.debian.org/science-team/keras-preprocessing
14 Vcs-Git: https://salsa.debian.org/science-team/keras-preprocessing.git
15 Homepage: https://keras.io/
16
17 Package: python3-keras-preprocessing
18 Architecture: all
19 Section: python
20 Depends:
21 python3-numpy:any,
22 Recommends:
23 python3-keras,
24 Description: data preprocessing module for the Keras deep learning framework
25 Keras is a Python library for machine learning based on deep (multi-
26 layered) artificial neural networks (DNN), which follows a minimalistic
27 and modular design with a focus on fast experimentation.
28 .
29 Features of DNNs like neural layers, cost functions, optimizers,
30 initialization schemes, activation functions and regularization schemes
31 are available in Keras a standalone modules which can be plugged together
32 as wanted to create sequence models or more complex architectures.
33 Keras supports convolutions neural networks (CNN, used for image
34 recognition resp. classification) and recurrent neural networks (RNN,
35 suitable for sequence analysis like in natural language processing).
36 .
37 It runs as an abstraction layer on the top of Theano (math expression
38 compiler) by default, which makes it possible to accelerate the computations
39 by using (GP)GPU devices. Alternatively, Keras could run on Google's
40 TensorFlow (not yet available in Debian).
41 .
42 Keras Preprocessing is the data preprocessing and data augmentation
43 module of the Keras deep learning library. It provides utilities for
44 working with image data, text data, and sequence data.