Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/csteinmetz1/cavae

Covert art variational autoencoder for generating new cover art

https://github.com/csteinmetz1/cavae

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.8%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Covert art variational autoencoder for generating new cover art

Basic Info
  • Host: GitHub
  • Owner: csteinmetz1
  • License: mit
  • Language: Python
  • Default Branch: master
  • Size: 207 KB
Statistics
  • Stars: 3
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 8 years ago · Last pushed almost 8 years ago
Metadata Files
Readme License

README.md

cavae

Covert art variational autoencoder for generating new cover art

Setup

``` get the code $ git clone https://github.com/csteinmetz1/cavae

create a virtual env $ virtualenv cavaeenv $ source cavaeenv/bin/activate

install dependancies $ pip install -r requirements.txt ```

Dataset

I am using a very small subset of the albums covers in this dataset, which contains over 1 million album covers. The dataset is split up into smaller .tar files by filename. I am using album_covers_s.tar, but feel free to use any or all of the archives.

Preprocessing

The dataset is quite messy and includes a lot of non-album cover images (different file formats, dead link images, non-square images, etc.), so to clean up the dataset for this project I created a script, clean.py, that iterates over every (.jpg) image in the user specified directory and does the following.

  • Check the dimensions - if not 1:1 aspect ratio discard the image
  • Resize the image - there is small ( 28, 28 ) and large ( 128, 128 )
  • Save the new images - user specificed output directory

Note: It took a significant amount of time to process all 100,000 images in album_covers_s.tar, about 1 hour.

covers

Here are some of the actual size ( 128, 128 ) covers after preprocessing.

Model

Owner

  • Name: Christian J. Steinmetz
  • Login: csteinmetz1
  • Kind: user
  • Location: London, UK
  • Company: @aim-qmul

Machine learning for Hi-Fi audio. PhD Researcher at C4DM.

GitHub Events

Total
Last Year

Issues and Pull Requests

Last synced: over 1 year ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

requirements.txt pypi
  • Keras ==2.2.0
  • Keras-Applications ==1.0.2
  • Keras-Preprocessing ==1.0.1
  • Markdown ==2.6.11
  • Pillow ==5.1.0
  • PyYAML ==3.12
  • Werkzeug ==0.14.1
  • absl-py ==0.2.2
  • astor ==0.6.2
  • bleach ==1.5.0
  • gast ==0.2.0
  • grpcio ==1.13.0
  • h5py ==2.8.0
  • html5lib ==0.9999999
  • numpy ==1.14.5
  • protobuf ==3.6.0
  • scipy ==1.1.0
  • six ==1.11.0
  • tensorboard ==1.8.0
  • tensorflow ==1.8.0
  • termcolor ==1.1.0