asc 0.3.0

Acoustic Scene Classification using Convolutional Neural Network

Acoustic Scene Classification

Development
Last release
PyPI status

Acoustic Scene Auditory (ASC) using Convolutional Neural Network (CNN) is a project being part of the Machine Learning Nanodegreen program given by Udacity. For a description of the proposal, you can refer to its web version.

Dataset

The dataset can be downloaded on the Zenodo server.

Features

• TODO

Credits

Project created by Matthieu Berjon and based on the work of Simone Battaglino, Ludovick Lepauloux and Nicholas Evans.

This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.

History

0.2.3 (2017-08-07)

Added

• Travis config file

• pytest suite

• CLI tests

• issue #5: Package coverage for the development setup

• issue #6: adding of a clear_zip() to clean the archive files

Changed

• Python 3.3 testing removed

Deprecated

• Nothing

Removed

• Nothing

Fixed

• Issue #4: invalid functools dependency

• Issue #7: update of docstring unzip_data()

Security

• Nothing

0.2.2 (2017-07-31)

Added

• nothing

Changed

• Updated of the ChangeLog (HISTORY.rst)

Deprecated

• nothing

Removed

• nothing

Fixed

• nothing

Security

• nothing

0.2.1 (2017-07-31)

Added

• nothing

Changed

• nothing

Deprecated

• nothing

Removed

• nothing

Fixed

• unzip_data() url list issue

• download of temporary files in the right directory

Security

• nothing

0.2.0 (2017-07-31)

Added

• Adding of a documentation (with docstrings)

• CLI command to download and unzip data automatically

• creation of a python package

• configuration of Tox

• download() method in data class

Changed

• Use of RST instead of markdown for all the documentation

• development packages are now in requirements_dev.txt

Deprecated

• nothing

Removed

• nothing

Fixed

• source files satisfy PEP8

• bug fix on getdata cli

Security

• Update of all packages to their latest versions

0.1.0 (2017-07-25)

• First release as a package.