Installation

VanillaNets is designed to be lightweight and easy to integrate into your Python environment. You can install the stable release via PyPI or build directly from the source if you plan to modify the framework.

System Prerequisites

Before installing, ensure your environment meets the following requirements. Because VanillaNets avoids bloated dependencies, these are the only two prerequisites:

• Python: Version 3.8 or higher.
• NumPy: Version 2.3.3 or higher (used as the core engine for all tensor operations).

Standard Installation (Recommended)

For most users, the easiest way to get started is by installing the pre-compiled package from PyPI using pip:

pip install vanillanets

Advanced: Installing from Source

If you intend to experiment with the underlying algorithms, add custom layers, or contribute to the project, you should install VanillaNets from the source code in "editable" mode.

1. Clone the repository to your local machine:

git clone https://github.com/UmarBalak/vanillanets.git
cd vanillanets

2. Install the package in editable mode:

pip install -e .

(Optional) If you plan to run the test suite or contribute code, install the development dependencies instead:

pip install -e ".[dev]"

Verify your installation

To confirm that the package and its core dependencies are correctly installed and accessible in your path, run the following diagnostic script in your Python environment or Jupyter Notebook:

import vanillanets
print(f"VanillaNets {vanillanets.__version__} initialized successfully!")

# Test importing the core architectural components
from vanillanets import Model, DenseLayer
from vanillanets.activations import ReLU, Sigmoid
from vanillanets.losses import BinaryCrossEntropy
from vanillanets.optimizers import Optimizer_Adam
from vanillanets.metrics import Accuracy

print("✓ Core components imported without errors. You are ready to build!")

If the script executes without throwing any ImportError, your environment is perfectly configured.

Next Steps

Now that your environment is set up, you can move on to the Quick Start guide to build and train your first neural network.