Update README.md
Browse files
README.md
CHANGED
|
@@ -95,6 +95,8 @@ The model performs exceptionally well on character identification (83.4% F1 acro
|
|
| 95 |
|
| 96 |
The macro optimized threshold is recommended as many "false positives" according to the benchmark are actually correct tags missing from the Danbooru dataset. The model frequently identifies appropriate tags that weren't included in the original tagging, making perceived accuracy higher than formal metrics suggest.
|
| 97 |
|
|
|
|
|
|
|
| 98 |
## 🧠 Architecture Overview:
|
| 99 |
|
| 100 |
### Vision Transformer Backbone:
|
|
|
|
| 95 |
|
| 96 |
The macro optimized threshold is recommended as many "false positives" according to the benchmark are actually correct tags missing from the Danbooru dataset. The model frequently identifies appropriate tags that weren't included in the original tagging, making perceived accuracy higher than formal metrics suggest.
|
| 97 |
|
| 98 |
+
**If you'd like to support further training on the complete dataset or my future projects, consider supporting me here:(https://ko-fi.com/camais). Your support will directly enable longer training runs and better models!**
|
| 99 |
+
|
| 100 |
## 🧠 Architecture Overview:
|
| 101 |
|
| 102 |
### Vision Transformer Backbone:
|