keras-preprocessing 1.1.0+ds-1 source package in Ubuntu
Changelog
keras-preprocessing (1.1.0+ds-1) unstable; urgency=medium [ Stephen Sinclair ] * New upstream version 1.1.0. * debian/watch: + add dversionmangle for +ds suffix. * debian/control: + update standard version to 4.5.0 (no changes). + add build-dep on python3-six. [ Anton Gladky ] * [5945435] Apply cme fix dpkg * [4a0786f] Use secure URI in Homepage field. * [09a4468] Bump debhelper from old 11 to 12. * [4fa23f7] Set upstream metadata fields: Bug-Database, Bug-Submit. -- Stephen Sinclair <email address hidden> Fri, 20 Mar 2020 15:55:44 +0000
Upload details
- Uploaded by:
- Debian Science Team
- Uploaded to:
- Sid
- Original maintainer:
- Debian Science Team
- Architectures:
- all
- Section:
- misc
- Urgency:
- Medium Urgency
Downloads
File | Size | SHA-256 Checksum |
---|---|---|
keras-preprocessing_1.1.0+ds-1.dsc | 2.1 KiB | 78f01b4e7f5654a19b7f27f3c1557e257a4ed93aae76cfb7e3b4138ea2c5f2d1 |
keras-preprocessing_1.1.0+ds.orig.tar.xz | 41.0 KiB | e9179d6552295217e972281642cb6c7a8af80470868efd3dcc2c023f1e5ffafd |
keras-preprocessing_1.1.0+ds-1.debian.tar.xz | 3.3 KiB | 85d66755368cf283412201a9a3f480d72f155f7fa3d963fdc5d281a03c519c1c |
Available diffs
- diff from 1.0.5-1 to 1.1.0+ds-1 (57.9 KiB)
No changes file available.
Binary packages built by this source
- python3-keras-preprocessing: data preprocessing module for the Keras deep learning framework
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).
.
Keras Preprocessing is the data preprocessing and data augmentation
module of the Keras deep learning library. It provides utilities for
working with image data, text data, and sequence data.