This project was developed as a submission for the IUB Hackathon. It features modules for data augmentation, model training, and object detection using YOLO. The aim is to deliver a proof-of-concept solution that leverages computer vision and deep learning techniques to address real-world challenges.
- Data Augmentation: Enhance your dataset using various augmentation techniques. See
augment.pyfor details. - Model Training: Build and train machine learning models with the provided scripts (
model.py). - Object Detection: Implement YOLO-based object detection for image processing tasks via
yoloObjectDetection.py. - Utility Functions: Organize and manage combined data class files using
moveCombinedDataClassFIles.py.
- Programming Language: Python
- Deep Learning & Computer Vision: YOLO for object detection and related frameworks
- Data Processing: Custom Python scripts for data augmentation and model training
- Notebooks: Jupyter Notebook files (if any) for exploratory analysis and evaluation
- Python 3.x
- Required Python packages (see
requirements.txtfor a full list)
- Clone the Repository:
git clone https://github.com/Ajayreddy-1234/KanyaRaasi-IUB-Hackathon.git
cd KanyaRaasi-IUB-Hackathon- Set Up a Virtual Environment:
python -m venv venv- Activate the Virtual Environment:
venv\Scripts\activate- Install Dependencies:
pip install -r requirements.txt- Data Augmentation: Run the augmentation script:
python augment.py- Model Training: Execute the model training script:
python model.py- Object Detection: Run the YOLO object detection module:
python yoloObjectDetection.py- augment.py: Script for augmenting your dataset.
- model.py: Script for building and training the machine learning model.
- moveCombinedDataClassFIles.py: Utility script for organizing or moving combined data class files.
- yoloObjectDetection.py: Module for executing YOLO-based object detection.
- Utilities/: Additional utility scripts and resources.
- requirements.txt: List of required Python packages.
- README.md: This file.
Contributions are welcome! Feel free to fork the repository and submit pull requests with improvements or bug fixes.
This project is open source and available under the MIT License.