ogkalu's picture
Update README.md
91a0149 verified
---
license: apache-2.0
---
RT-DETR-v2 r50vd model fine-tuned on about 11k Manga, Webtoon, Manhua and Western Comic style Images for text and speech bubble detection.<br>
Training Image Size = 640. Training Images were resized, not cropped.<br>Tall Webtoons were split vertically.<br>
Classes are:<br>
0: bubble<br>
1: text_bubble (text inside bubbles)<br>
2: text_free (text outside bubbles)<br>