https://github.com/christophschuhmann/improved-aesthetic-predictor

CLIP+MLP Aesthetic Score Predictor
https://github.com/christophschuhmann/improved-aesthetic-predictor

Last synced: 8 days ago
JSON representation

CLIP+MLP Aesthetic Score Predictor

• Host: GitHub
• URL: https://github.com/christophschuhmann/improved-aesthetic-predictor
• Owner: christophschuhmann
• License: apache-2.0
• Created: 2022-06-25T20:57:49.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-07-01T11:58:57.000Z (4 months ago)
• Last Synced: 2024-08-01T13:29:11.968Z (3 months ago)
• Language: Python
• Homepage:
• Size: 9.72 MB
• Stars: 819
• Watchers: 6
• Forks: 86
• Open Issues: 12
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# CLIP+MLP Aesthetic Score Predictor

Train, use and visualize an aesthetic score predictor ( how much people like on average an image ) based on a simple neural net that takes CLIP embeddings as inputs.

Link to the AVA training data ( already prepared) :

https://drive.google.com/drive/folders/186XiniJup5Rt9FXsHiAGWhgWz-nmCK_r?usp=sharing

Visualizations of all images from LAION 5B (english subset with 2.37B images) in 40 buckets with the model sac+logos+ava1-l14-linearMSE.pth:

http://captions.christoph-schuhmann.de/aesthetic_viz_laion_sac+logos+ava1-l14-linearMSE-en-2.37B.html