update readme

README.md

@@ -2,21 +2,26 @@
 
 attempting to create a more readable evaluation to anime tagger ai systems
 
+companion article: https://l4.pm/wiki/Personal%20Wiki/AI%20stuff/understanding%20anime%20taggers.html
+
 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)
+score formula: f1
 
 then average for all posts
 
 system dependencies:
  - python3
- - [stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) with the [tagger extension](https://github.com/toriato/stable-diffusion-webui-wd14-tagger)
+
+on a system with cpu:
  - [hydrus-dd](https://gitgud.io/koto/hydrus-dd)
 
+on a system with gpu:
+ - [stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) with the [tagger extension](https://github.com/toriato/stable-diffusion-webui-wd14-tagger)
+ - [wdv3-timm](https://github.com/neggles/wdv3-timm)
+
 ```sh
 python3 -m venv env
 env/bin/pip install -Ur ./requirements.txt
@@ -45,4 +50,4 @@ env/bin/python3 ./main.py scores
 # keep in mind that you can download more images, run fight mode, and then
 # run score mode! the commands are aware of work that's been already done and
 # will only run the tagger models for the new files
-```
+```

main.py

@@ -567,7 +567,7 @@ async def scores(ctx):
     )
 
     print("md table")
-    print("| model | score | avg. runtime |")
+    print("| model | score | avg. runtime (ms) |")
     print("| ---- | ---- | ---- |")
     for model in sorted(
         normalized_scores.keys(),