Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/coffeevampir3/easy-aesthetic-predictor
A repository for making an aesthetic prediction model based on the ConvneXt architecture.
https://github.com/coffeevampir3/easy-aesthetic-predictor
aesthetic-assessment convnext gradio jupyter-notebook neural-network
Last synced: 3 days ago
JSON representation
A repository for making an aesthetic prediction model based on the ConvneXt architecture.
- Host: GitHub
- URL: https://github.com/coffeevampir3/easy-aesthetic-predictor
- Owner: CoffeeVampir3
- Created: 2024-02-18T04:08:48.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2024-02-18T05:24:06.000Z (9 months ago)
- Last Synced: 2024-02-19T05:21:39.132Z (9 months ago)
- Topics: aesthetic-assessment, convnext, gradio, jupyter-notebook, neural-network
- Language: Jupyter Notebook
- Homepage:
- Size: 18.6 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## How to use:
Use the included gradio demo to get simple predictions on images, see how it feels. Demo will automatically download pretrained weights from for you to try. You can rip the inference code out of the gradio demo and use it in any python script or whatever, feel free. This model is likely very overfit on my aesthetic preferences, the idea with this is to reduce the amount of work required to prep datasets, so you likely want to tune it to your preferences instead. Additionally, this was only trained on anime images.
## Training:
See the wiki, it's designed to be pretty easy. You do need a GPU to train. https://github.com/CoffeeVampir3/easy-aesthetic-predictor/wiki