Hugging Face's logo

BaseerAI
/
Interfuser-Baseer-v1

Object Detection
PyTorch
English
computer-vision
autonomous-driving
self-driving-car
end-to-end
transformer
attention
positional-encoding
carla
trajectory-prediction
Model card Files
xet
Community
Interfuser-Baseer-v1 / README.md
altawil
Update README.md
98f47c2 verified
preview code
|
raw
history blame
4.47 kB
metadata
license: mit
language:
  - en
library_name: pytorch
tags:
  - computer-vision
  - autonomous-driving
  - self-driving
  - interfuser
  - carla
  - object-detection
  - trajectory-prediction
datasets:
  - PDM-Lite-CARLA
pipeline_tag: object-detection

🚗 InterFuser-Baseer-v1: Autonomous Driving Model

License: MIT PyTorch CARLA

📖 Overview

InterFuser-Baseer-v1 is a state-of-the-art transformer-based model for autonomous driving, specifically fine-tuned for the Baseer Self-Driving API. This model combines computer vision and deep learning to provide real-time traffic object detection and trajectory planning in simulated driving environments.

🎯 Key Capabilities

  • Multi-Task Learning: Simultaneous traffic object detection and waypoint prediction
  • Transformer Architecture: Advanced attention mechanisms for scene understanding
  • Real-Time Processing: Optimized for real-time inference in driving scenarios
  • CARLA Integration: Specifically tuned for CARLA simulation environment

🏗️ Architecture

Model Components

Component Specification
Image Backbone ResNet-50 (ImageNet pretrained)
LiDAR Backbone ResNet-18 (disabled in this version)
Transformer 6-layer encoder/decoder, 8 attention heads
Embedding Dimension 256
Prediction Heads GRU-based waypoint predictor + Detection head

Output Format

  • Traffic Detection: 20×20×7 grid (confidence, position, dimensions, orientation)
  • Waypoint Prediction: 10 future trajectory points
  • Scene Understanding: Junction, traffic light, and stop sign detection

🚀 Quick Start

Installation 

pip install torch torchvision timm huggingface_hub

Usage Example 

import torch
from huggingface_hub import hf_hub_download

# Download model weights
model_path = hf_hub_download(
    repo_id="Adam-IT/Interfuser-Baseer-v1",
    filename="best_model.pth"
)

# Load model (requires InterFuser class definition)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = torch.load(model_path, map_location=device)
model.eval()

# Inference
with torch.no_grad():
    outputs = model(input_data)

📊 Performance

Training Details

  • Dataset: PDM-Lite-CARLA (Urban driving scenarios)
  • Training Objective: Multi-task learning with IoU optimization
  • Framework: PyTorch

Key Metrics

  • Optimized for traffic detection accuracy
  • Enhanced bounding box IoU performance
  • Robust waypoint prediction in urban scenarios

⚠️ Limitations

Current Constraints

  • Simulation Only: Trained exclusively on CARLA data
  • Single Camera: Front-facing camera view only
  • No LiDAR: Vision-based approach without LiDAR fusion
  • Dataset Scope: Limited to PDM-Lite-CARLA scenarios

Recommended Use Cases

  • ✅ CARLA simulation environments
  • ✅ Research and development
  • ✅ Autonomous driving prototyping
  • ❌ Real-world deployment (requires additional training)

🛠️ Integration

This model is designed to work with:

  • Baseer Self-Driving API
  • CARLA Simulator
  • PyTorch Inference Pipeline
  • Custom Autonomous Driving Systems

📚 Citation

If you use this model in your research, please cite:

@misc{interfuser-baseer-v1,
  title={InterFuser-Baseer-v1: Fine-tuned Autonomous Driving Model},
  author={Adam-IT},
  year={2024},
  publisher={Hugging Face},
  howpublished={\url{https://huggingface.co/Adam-IT/Interfuser-Baseer-v1}}
}

👨‍💻 Development

Developed by: Adam-IT
Project Type: Graduation Project - AI & Autonomous Driving
Institution: [Your Institution Name]

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🤝 Contributing

Contributions, issues, and feature requests are welcome! Feel free to check the issues page.

📞 Support

For questions and support:

  • Create an issue in this repository
  • Contact: [Your Contact Information]
🚗 Drive the Future with AI 🚗