Model Card

Roof detection model for remote sensing imagery, fine-tuned using RT-DETR.

Example Prediction

The following example shows roof detections produced by the model:

Model Details

Model Description

• Model type: Object Detection for Remote Sensing task.
• License: MIT

Model Sources

• GitHub: Jupyter Notebook

Try it

• Interactive Demo: Satellite Roof Annotation - Hugging Face Space
• MCP Tool: Connect to Gradio MCP server to use this model from MCP-compatible clients such as Claude Code, Cursor, and Codex.

Limitations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import AutoModelForObjectDetection, AutoImageProcessor
import torch
import cv2

image_path=YOUR_IMAGE_PATH
image = cv2.imread(image_path)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

model = AutoModelForObjectDetection.from_pretrained("Yifeng-Liu/rt-detr-finetuned-for-satellite-image-roofs-detection")
image_processor = AutoImageProcessor.from_pretrained("Yifeng-Liu/rt-detr-finetuned-for-satellite-image-roofs-detection")


CONFIDENCE_TRESHOLD = 0.5

with torch.no_grad():
    model.to(device)

    # load image and predict
    inputs = image_processor(images=image, return_tensors='pt').to(device)
    outputs = model(**inputs)

    # post-process
    target_sizes = torch.tensor([image.shape[:2]]).to(device)
    results = image_processor.post_process_object_detection(
        outputs=outputs,
        threshold=CONFIDENCE_TRESHOLD,
        target_sizes=target_sizes
    )[0]