title | emoji | sdk | sdk_version | app_file | license | link |
---|---|---|---|---|---|---|
Car Design Analysis |
🐨 |
gradio |
3.38.0 |
app.py |
mit |
Image from: https://deepvisualmarketing.github.io/
CarEpochClassifier is a machine learning-based project that employs computer vision and deep learning techniques to provide comprehensive analysis and insights about cars from their visual data. This system goes beyond conventional image recognition and classification, instead offering chronological (temporal) classification, morphological classification, a modernity score based on model year, and a typicality score indicating the car's typical appearance for its body type and model year.
- Temporal Classification: Estimation of the car's model year.
- Morphological Classification: Identifies the body type of the car (e.g., Hatchback, SUV, MPV, Saloon, Convertible).
- Modernity Score: Calculates a modernity score based on the estimated model year.
- Typicality Score: Compares the car's appearance to the typical appearance of cars in its estimated year range and body type.
The project relies heavily on the following frameworks and libraries:
- PyTorch
- Detectron2
- Gradio
- torchvision
- sklearn
- cv2
- numpy
- PIL
Clone this GitHub repository to your local machine.
git clone https://github.com/Suraj-Bhor/CarEpochClassifier
This project requires Python 3.8 or above. Install the required packages using pip:
pip install -r requirements.txt
Execute the main Python script to start the Gradio interface.
python app.py
You will be presented with a Gradio interface where you can upload images of cars to be classified.
This project makes use of the Deep Visual Marketing dataset, which provides a rich source of 1,451,784 images from 899 UK market car models.