Getting Started

Welcome to Image ML Pod, a framework for building modular machine learning applications on image datasets. This guide will help you set up your environment and introduce the essential tools integrated into the pod.

🚀 Setup

Follow these steps to prepare your environment:

  1. Create a Virtual Environment
    Use Python’s venv or Conda to isolate your development environment. For example, with venv:

    python -m venv .env

  2. Clone the Repository
    Clone the repository to your local machine using Git.

  3. Install the Package
    Install the project in editable mode for development flexibility:

    pip install -e .

  4. Install Dependencies
    Use the provided requirements.txt file to install all dependencies:

    pip install -r requirements.txt

You’re now ready to start exploring the pod!

🛠 Workflow Management with Kedro

We’ve chosen Kedro as the backbone for workflow management due to its modular structure and intuitive pipeline design. With Kedro, you can easily manage:

  • Data workflows: Organize data inputs and outputs.
  • Pipeline modularity: Create reusable and scalable pipelines.
  • Seamless collaboration: Maintain clear separation of concerns.

📚 Learn More: Explore the Kedro documentation for a comprehensive overview.

✅ Pre-commit Hooks

To keep your project clean and automated, we’ve configured pre-commit hooks for:

  1. Linting: Enforces consistent code style and formatting. Learn more here.
  2. Testing: Automates tests to ensure code reliability. Learn more here.
  3. Automatic Documentation Generation: Keeps your documentation synchronized with your codebase.

Install the Hooks

Activate the pre-commit hooks by running:

pre-commit install

From this point forward, these hooks will automatically check your code on each commit, ensuring high standards across the board.