---
license: other
license_name: umamusume-derivativework-guidelines
license_link: https://umamusume.jp/derivativework_guidelines/
---

This is the model repository for ULTIMA-YOLOv9, containing the following checkpoints:
- YOLO9-E

# About **ULTIMA-YOLO** models

This is a part of [ULTIMA](https://huggingface.co./datasets/UmaDiffusion/ULTIMA) project.

ULTIMA-YOLOv9 model is a facial detection model for Uma Musumes in illustrations and based on [yolov9-e](https://arxiv.org/abs/2402.13616) and [ULTIMA-YOLO dataset](https://huggingface.co./datasets/UmaDiffusion/ULTIMA-YOLO)

[ULTIMA Dataset](https://huggingface.co./datasets/UmaDiffusion/ULTIMA) is **U**ma Musume **L**abeled **T**ext-**I**mage **M**ultimodal **A**lignment Dataset.   


### How to Use

Clone YOLOv9 repository.

```
git clone https://github.com/WongKinYiu/yolov9.git
cd yolov9
```

Download the weights using `hf_hub_download` and use the loading function in helpers of YOLOv9.

```python
from huggingface_hub import hf_hub_download 
hf_hub_download("UmaDiffusion/ULTIMA-YOLOv9", filename="ultima_yolov9-e.pt", local_dir="./")
```

Load the model.

```python
# make sure you have the following dependencies
import torch
import numpy as np
from models.common import DetectMultiBackend
from utils.general import non_max_suppression, scale_boxes
from utils.torch_utils import select_device, smart_inference_mode
from utils.augmentations import letterbox
import PIL.Image

@smart_inference_mode()
def predict(image_path, weights='ultima_yolov9-e.pt', imgsz=640, conf_thres=0.1, iou_thres=0.45):
    # Initialize
    device = select_device('0')
    model = DetectMultiBackend(weights='yolov9-e.pt', device="0", fp16=False, data='data/coco.yaml')
    stride, names, pt = model.stride, model.names, model.pt

    # Load image
    image = np.array(PIL.Image.open(image_path))
    img = letterbox(img0, imgsz, stride=stride, auto=True)[0]
    img = img[:, :, ::-1].transpose(2, 0, 1)
    img = np.ascontiguousarray(img)
    img = torch.from_numpy(img).to(device).float()
    img /= 255.0
    if img.ndimension() == 3:
        img = img.unsqueeze(0)

    # Inference
    pred = model(img, augment=False, visualize=False)

    # Apply NMS
    pred = non_max_suppression(pred[0][0], conf_thres, iou_thres, classes=None, max_det=1000)
```