29 projects
albumentationsx
Fast, flexible, and advanced augmentation library for deep learning, computer vision, and medical imaging. Albumentations offers a wide range of transformations for both 2D (images, masks, bboxes, keypoints) and 3D (volume data, volumetric masks, keypoints) data, with optimized performance and seamless integration into ML workflows. Licensed under AGPL-3.0-only; alternative commercial terms are also available.
albucore
High-performance image processing functions for deep learning and computer vision.
albu-spec
Extract comprehensive metadata from Albumentations transforms including parameters, types, constraints, and docstrings
google-docstring-parser
A lightweight, efficient parser for Google-style Python docstrings that converts them into structured dictionaries.
albumentations
Fast, flexible, and advanced augmentation library for deep learning, computer vision, and medical imaging. Albumentations offers a wide range of transformations for both 2D (images, masks, bboxes, keypoints) and 3D (volumes, volumetric masks, keypoints) data, with optimized performance and seamless integration into ML workflows.
docstring2json
A tool to convert Google-style docstrings to JSON format
google-docstring-2tsx
A tool to convert Google-style docstrings to TSX format for Next.js documentation
yolo5face
Wrapper over Yolo5Face for a more convenient inference.
html2info
A package to parse raw HTML and return structured information.
clip2classdist
A Python script that analyzes image classes using OpenAI CLIP model
ternaus-cleantext
Clean text from extra spaces and special symbols as in the CLIP model.
getsimilar
Image search: image/text => images.
image2base64
Image to base64 and back.
insightfacewrapper
Wrapper over insightface for a more convenient inference.
addlogo
Add logo.
base64-to-image
Image to base64 and back.
retinaface-pytorch
Retinaface implementation in Pytorch.
datasouls-antispoof
Detect spoofing attack
iglovikov-helper-functions
Unstructured set of the helper functions.
check-orientation
Check if image was rotated by 90, 180, 270 degrees.
midv500models
Document segmentation.
cloths-segmentation
High quality model for cloths segmentation.
people-segmentation
High quality model for people segmentation.
facemask-detection
Unstructured set of the helper functions.
albumentations-experimental
Experimental functionality for the Albumentaions library.
ternausnet
UNet with VGG encoders
lyft-dataset-sdk
SDK for Lyft dataset.
imread-benchmark
Benchmark for image reading for different libraries.
