fast-augment 0.1.2

One-command image augmentation

FastAugment 🚀

One-command image augmentation for computer vision pipelines. Apply transformations with a single function call.

Features

• 🛠️ Preset-based augmentations - Choose between "simple" or "advanced" augmentation strategies
• 🖼️ Supports multiple input types - Works with image paths, numpy arrays, and PyTorch datasets
• ⚡ Efficient processing - Optimized OpenCV backend
• 📁 Automatic saving - Optionally save augmented images to directory

Installation

pip install fastaugment

Quick Start

Basic Usage

from fastaugment import FastAugment
import cv2

# Load an image
image = cv2.imread("image.jpg")
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

# Initialize augmenter
augmenter = FastAugment(preset="advanced")

# Augment single image
augmented_image = augmenter.augment_image(image)

Dataset Augmentation

from torchvision.datasets import CIFAR10

# Load dataset
dataset = CIFAR10(root="./data", train=True)

# Augment entire dataset
augmenter = FastAugment(preset="advanced")
augmented_data = augmenter.augment_dataset(
    dataset=dataset,
    output_dir="./augmented_data",
    target_size=10000
)

Presets

Preset	Transformations
simple	Horizontal flips, rotations
advanced	Adds cutout and brightness/contrast

Advanced Configuration

Customize individual augmentation probabilities:

# Coming in v1.1 (create feature request!)

Documentation

Full API reference available at fastaugment.readthedocs.io

Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

License

Distributed under the MIT License. See LICENSE for more information.

Contact

Aryan Patil - [e-mail]