YOLOV8N Manga Frame Segmentation
This model is a fine-tuned YOLOV8N-seg for detecting and segmenting frames in manga images.
Usage
from ultralytics import YOLO
from huggingface_hub import hf_hub_download
# Download and load the model
model_path = hf_hub_download(repo_id="TheBlindMaster/yolov8n-manga-frame-seg", filename="best.pt")
model = YOLO(model_path)
# Run inference
results = model.predict("manga_page.jpg")
Training Details
- Base Model: yolov8n-seg.pt
- Dataset: Manga109 with MangaSegmentation annotations
- Task: Frame instance segmentation
- Epochs: 1
- Image Size: 320
- Batch Size: 16
Categories
Trained to detect: frame
- Downloads last month
- 155