/improved-aesthetic-predictor-batch

CLIP+MLP Aesthetic Score Predictor. With batch processing and sorting.

Primary LanguagePythonApache License 2.0Apache-2.0

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.

Added batch processing of images for scoring. It prints filenames with their scores in descending order.

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