Skip to main content

Acoustic Scene Classification using Convolutional Neural Network

Project description

Acoustic Scene Classification

Development

Travis CI builds Coverall coverage report

Last release

PyPI Latest Version Python versions (PyPI) Updates

PyPI status

Distribution format (PyPI) Project status (PyPI) License (PyPI)

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

0.3.1 (2017-08-22)

Added

  • Issue #8: config file feature

  • Issue #11: Samplerate setting up through CLI

  • Issue #10: Spectrogram calculation

  • Issue #24: Add a ‘config’ subcommand to the CLI

  • Issue #25: Read a value from the config file

  • Issue #21: Script to verify the samplerate sanity of the database

  • Issue #30: Function to transform milliseconds to samples

Changed

  • Issue #23: Update of the documentation for the installation process

  • Issue #26: Update of the CLI subcommand ‘getdata’

  • Issue #32: Exception handling in config reading

Deprecated

Nothing.

Removed

Nothing.

Fixed

  • Issue #9: trailing slash on data path

  • Issue #13: Update of the config file parameters

  • Issue #15: Crash when setting up the samplerate

  • Issue #22: Update of the dependency list

  • Issue #25: Update of the config file

  • Update of docstrings

  • Update of the documentation

Security

  • Update of the Coveralls library from 1.1 to 1.2.0

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.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

asc-0.3.1.tar.gz (30.7 kB view details)

Uploaded Source

Built Distribution

asc-0.3.1-py2.py3-none-any.whl (11.8 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file asc-0.3.1.tar.gz.

File metadata

  • Download URL: asc-0.3.1.tar.gz
  • Upload date:
  • Size: 30.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No

File hashes

Hashes for asc-0.3.1.tar.gz
Algorithm Hash digest
SHA256 f05b320fba6ee09b51b661d57470f47d3b8f3865f32a3aad7c610f9d7d37239c
MD5 9525e2c8c2d547be5ab0c33cb4b03a83
BLAKE2b-256 4f17aa7d38d623b08344ffe4a6dc6b348415e341ffd87239c65c2e370bf178d6

See more details on using hashes here.

File details

Details for the file asc-0.3.1-py2.py3-none-any.whl.

File metadata

File hashes

Hashes for asc-0.3.1-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 cc21a48993a090ed2fc7b5f6325a81c4d4da90f19d1c2efe5594147aaa6152e7
MD5 f08844d30c91161dc5a98e2d18d61e3c
BLAKE2b-256 f6cd71af4dcd853acee529e649de2cae8b4caaaa8f1ec4e32db2c4f524b2add4

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page