A newer version of the Gradio SDK is available: 6.22.0
metadata
title: Vehicle Classification Model
emoji: 🐨
colorFrom: yellow
colorTo: red
sdk: gradio
sdk_version: 6.9.0
app_file: app.py
pinned: false
license: apache-2.0
short_description: A CNN for vehicle perception with 78.54% accuracy.
title: Vehicle Classification Demo - UTD emoji: 🏎️ colorFrom: blue colorTo: indigo sdk: gradio sdk_version: 5.16.0 app_file: app.py pinned: true license: apache-2.0 short_description: Custom CNN for Autonomous Vehicle Perception
🏎️ Vehicle Classification: Autonomous Perception Demo
This application provides a real-time inference interface for a custom-built CNN architecture designed for safety-critical vehicle classification.
📊 Model Performance
- Final Test Accuracy: 78.54% (Target: >50%)
- Generalization Gap: 0.06% (Minimal variance between training and test sets)
- Classes: 8 (Bicycle, Bus, Car, Motorcycle, NonVehicles, Taxi, Truck, Van)
🏗️ Technical Architecture
Unlike generic transfer learning, this model utilizes a Custom CNN designed for high transparency:
- Architecture: 3-stage Convolutional blocks (16, 32, 64 filters).
- Safety Regularization: Integrated Dropout (0.5) and BatchNorm2d to ensure the model learns global geometric features rather than overfitting on pixel-level noise.
- Preprocessing: Standardized 224x224 input with ImageNet-standard normalization.
🛡️ AI Safety Analysis
- Critical Detection: The model is highly optimized to distinguish
NonVehicles(1,775/1,800 correct), minimizing the risk of "false positive" emergency braking events. - Robustness: Maintained high performance on the test set despite diverse lighting and perspective variations in the original dataset.
📚 More Work & Research Portfolio
This project is part of my broader commitment to AI/CS research and open-source development.
🔗 Links for this project
🛠️ Other Key Projects
- Language Datasets: Curated and published 100k+ rows datasets for low resource languages on Hugging Face for regional NLP research.
- CNSD Model Architecture: Authored research on neural network configurations for optimized feature extraction.
- Custom 4 sentiment models, 1 vehicle classification model and several datasets.
- Link to my Hugging Face account : https://huggingface.co/abhiprd20 (with all models and datasets)
- My NLP research paper pre-print : https://zenodo.org/records/19054785
- 2nd research project : https://github.com/abhiprd200/CNSD_prototype
- Demo of this project: Live on Hugging Face Spaces
- My github with other projects : https://github.com/abhiprd200
Contact
- E-mail : abhiprd20@gmail.com
License: Apache 2.0
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference