Machine Vision

Packaged version of the Strongsort repository

A toolkit for making real world machine learning and data analysis applications

Huggingface bolts for geniusrise

Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.

SDK API to assess image Machine Learning models.

ModeYOLO is a versatile Python package designed for efficient color space transformations and simplified dataset modification for deep learning applications. Seamlessly integrating into your workflow, this package empowers users to effortlessly perform diverse color operations and streamline the creation of modified datasets, enhancing the flexibility and convenience of machine learning model training processes.

Wrapper for the incoming yolov9

Support for book: Robotics, Vision & Control 3 in Python

A library and command line utility for detecting face masks in images and video streams

Application to quickly build machine vision pipelines with little or no code

Video streaming inference framework, integrating image algorithms and models for real-time/offline video structuring

Packaged version of the BSRGAN repository

Autocare Tx Model

Visym Collector

Solution for Kaggle competition https://www.kaggle.com/c/dogs-vs-cats

Ultralytics YOLO for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.

A Python-based utility library for databases, computer vision, signal processing, and machine learning

Deep Learning Projects base on OpenMMLab.

With no prior knowledge of machine learning or device-specific deployment, you can deploy a computer vision model to a range of devices and environments using Roboflow Inference CLI.

Differentiable foveated vision for Deep Learning methods

TorchHandle makes your PyTorch development more efficient and make you use PyTorch more comfortable

SDK API to assess image Machine Learning models.

Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.

Extracts the Machine Readable Zone (MRZ) data from document images

Vision Xformers

Open, Clean Datasets for Computer Vision.

Automatically create Gradio apps from YOLOv5 models and push to the Space.

A small example package

iCreativeFactor's library for autonomous system.

Packaged version of the Yolov5 object detector

Packaged version of the Yolov5 object detector

A Python Library for Computer Vision tasks like Object Detection, Segmentation, Pose Estimation etc

Easiest way of fine-tuning HuggingFace video classification models.

A Python library including general functions and operations on various computer vision related structures.

quinine is a library for configuring machine learning projects.

A Tensor library in Python, built in C++

Torch Multimodal Supervised Triplet Learning Toolbox

DetHub: Object Detection Model Hub

Collection of requisites to speed up research & development with PyTorch

Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.

Wrapper for incomming yolov7

A Python package designed for capturing images from multiple cameras simultaneously. MCCP simplifies the process of data collection for machine learning models and setting up computer vision applications.

ML score check: checking the validity of machine learning and computer vision scores

Data files for the Machine Vision Toolbox for Python.

Easy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint

State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow

Rice High Throughput Phenotyping Computer Vision Toolkit

Flax Image Models

Optimize RandAugment with differentiable operations