README.md

---
license: mit
tags:
  - yolo11
  - ultralytics
  - image-segmentation
  - deep-learning
  - satellite
  - rso-detection
datasets:
  - custom
library_name: ultralytics
base_model: yolo11
pipeline_tag: image-segmentation
inference: true
widget:
  - src: "example_image.jpg"
    example_title: "RSO Detection"
model-index:
  - name: best
    results:
      - task:
          type: image-segmentation
          name: Instance Segmentation
        dataset:
          name: RSO Detection Dataset
          type: custom
        metrics:
          - name: Mean Average Precision (mAP@50)
            type: mean_average_precision
            value: 0.8750
          - name: Mean Average Precision (mAP@50-95)
            type: mean_average_precision
            value: 0.6194
fine-tuned-from: Ultralytics/YOLO11
labels:
  - streak
metadata:
  label2id:
    streak: 0
  id2label:
    0: streak
---

# best

## Model Information
This is a YOLO11-based segmentation model for detecting Resident Space Objects (RSOs) in satellite imagery.

## Classes
- **streak**: Class 0

## Usage
```python
from huggingface_hub import InferenceClient

client = InferenceClient(model="best")
result = client.image_segmentation(image)
```

## Training Metrics
- mAP@50: 0.8750
- mAP@50-95: 0.6194