Object Detection
ultralytics
PyTorch
English
yolov12
watermark-detection
dinov3
vision-transformer
Eval Results (legacy)
Instructions to use corzent/yolov12x-dino3-watermark-detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use corzent/yolov12x-dino3-watermark-detection with ultralytics:
from ultralytics import YOLOvv12 model = YOLOvv12.from_pretrained("corzent/yolov12x-dino3-watermark-detection") source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle

- Xet hash:
- df71c9384fd08dfc51258f42610a5fd715f32dac2fd2bce1a00794e1cd7e7dab
- Size of remote file:
- 103 kB
- SHA256:
- e5d972fc88312dc74bf195a2601c2d470dc885c1e5210ec55a0e531ef2615eda
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.