attempting to create a more readable evaluation to anime tagger ai systems
Go to file
Luna 389a582e39 add histogram plotting of scores 2023-06-10 15:26:02 -03:00
.gitignore add histogram plotting of scores 2023-06-10 15:26:02 -03:00
LICENSE Initial commit 2023-06-10 00:41:46 +00:00
README.md add download_images function 2023-06-09 23:19:15 -03:00
config.example.json add download_images function 2023-06-09 23:19:15 -03:00
main.py add histogram plotting of scores 2023-06-10 15:26:02 -03:00
requirements.txt add histogram plotting of scores 2023-06-10 15:26:02 -03:00

README.md

tagger-showdown

attempting to create a more readable evaluation to anime tagger ai systems

idea: take some recent images from danbooru, also include your own

then run x tagger systems against each other

score formula:

(len(tags in ground_truth) - len(tags not in ground_truth)) / len(ground_truth)

then average for all posts

python3 -m venv env
env/bin/pip install -Ur ./requirements.txt
env/bin/python3 ./main.py