This project utilizes the "V2 Plant Seedlings Dataset", which comprises 5,539 images of crop and weed seedlings at different growth stages, which can be found on Kaggle: Plant Seedlings Classification Dataset. The dataset is richly diverse, containing 12 distinct plant species common in Danish agriculture. Each class consists of RGB images showing plants at various growth stages, making it a perfect dataset for our classification task.
- Data Preparation: Understand your data with comprehensive visualizations.
- Model Building: Leverage a pre-trained ResNet18 model using PyTorch, tailored for the classification task.
- Model Training and Validation: Detailed guidance on training the model with real-time performance feedback.
- Model Evaluation: Techniques to rigorously evaluate the model's performance on unseen data.
- Result and Visualization: Tools for analyzing and visualizing the model's predictions.
To get started with this project:
- Clone this repository to your local machine.
- Ensure you have Jupyter Notebook installed and running.
- Install the required dependencies.
- Download the "Plant Seedlings Classification Dataset" and place it in the designated directory.
- Open and run the Jupyter Notebook "Plant_Seedlings_Classification.ipynb" to train and evaluate the model.
We welcome contributions to enhance the functionality and efficiency of this script. Feel free to fork, modify, and make pull requests to this repository. To contribute:
- Fork the Project.
- Create your Feature Branch (
git checkout -b feature/AmazingFeature). - Commit your Changes (
git commit -m 'Add some AmazingFeature'). - Push to the Branch (
git push origin feature/AmazingFeature). - Open a Pull Request against the
mainbranch.
This project is licensed under the MIT License - see the LICENSE file for details.
Author: Akhil Chhibber
LinkedIn: https://www.linkedin.com/in/akhilchhibber/
Medium Blogs: https://medium.com/@akhil.chibber