Sourcify
Effortlessly find and manage open-source dependencies for your projects.

A Python library for image augmentation in machine learning.

Augmentor is a Python library designed to perform image augmentation for machine learning tasks. It provides a standalone, platform-independent solution to expand datasets, particularly for neural networks and deep learning models. The library employs a stochastic pipeline approach, where augmentation operations are applied probabilistically. Users can create pipelines with rotations, zooms, flips, and distortions. It supports multi-threading for faster processing and allows for augmentation of ground truth data in parallel with original images, suitable for tasks like image segmentation. Augmentor can be integrated with Keras and PyTorch, offering generators for on-the-fly data augmentation during training.
Augmentor is a Python library designed to perform image augmentation for machine learning tasks.
Explore all tools that specialize in image augmentation. This domain focus ensures Augmentor delivers optimized results for this specific requirement.
Applies elastic distortions to images, creating realistic variations while preserving labels. It uses per-pixel displacement maps to warp the image.
Offers 12 different types of perspective transforms, including tilt, skew, and corner distortion, using projective transformations.
Augments ground truth data (masks, bounding boxes) in parallel with original images, ensuring consistent transformations.
Allows augmenting multiple masks or images associated with a single input image, providing flexibility for complex data structures.
Provides generators for Keras and PyTorch, allowing for on-the-fly data augmentation during model training.
Install Augmentor using pip: `pip install Augmentor`
Import the Augmentor library in your Python script: `import Augmentor`
Instantiate a Pipeline object, pointing to your image directory: `p = Augmentor.Pipeline("/path/to/images")`
Add augmentation operations to the pipeline, specifying probabilities and parameters, e.g., `p.rotate(probability=0.7, max_left_rotation=10, max_right_rotation=10)`
Sample from the pipeline to generate augmented images: `p.sample(10000)`
Alternatively, process each image in the pipeline exactly once using `p.process()`
For ground truth data, use the `ground_truth()` function to augment masks in parallel
All Set
Ready to go
Verified feedback from other users.
"Users praise Augmentor for its ease of use, flexibility, and effectiveness in improving model accuracy through data augmentation."
Post questions, share tips, and help other users.
Effortlessly find and manage open-source dependencies for your projects.

End-to-end typesafe APIs made easy.

Page speed monitoring with Lighthouse, focusing on user experience metrics and data visualization.

A multi-voice text-to-speech system emphasizing quality and realistic prosody.

Topcoder is a pioneer in crowdsourcing, connecting businesses with a global talent network to solve technical challenges.

Explore millions of Discord Bots and Discord Apps.