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.
Chess board recognition toolkit
Numpy-native operator library for vision, 3-D and measurement (3,838 typed ops in the machine-readable index: imaging, point clouds, optics, tomography, metrology) with an evolutionary pipeline designer and honest holdout gating
Hardware Abstraction Layer for edge AI with zero-copy tensors, image processing, and YOLO decoding
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
Declarative machine learning: End-to-end machine learning pipelines using data-driven configurations.
Fork of Albumentations in direct support of NRTK (Natural Robustness Toolkit). Fast, flexible, and advanced augmentation library for deep learning, computer vision, and medical imaging. 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.
doc2text drastically improves the extraction of text from images by fixing resolution, text area (crop), and skew.
Visiongraph is a computer-vision pipeline library designed to simplify the prototyping of image-based algorithms
A lightweight Computer Vision library for high-performance AI research - Modern Computer Vision on the Fly.
Sipeed Maix Vision Python SDK
The official implementation of visual priors from the paper Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies. Arxiv preprint 2018.
Python bindings for the Novitec machine vision camera API (Windows x86-64)
Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
TorchSeg: Semantic Segmentation models for PyTorch
Visynx Python SDK: run your Visynx computer vision models (object detection, segmentation, pose, classification) hosted or on your own hardware, including NVIDIA Jetson.
Extracts the Machine Readable Zone (MRZ) data from document images
Train models with self-supervised learning in a single command
OpenMV Camera Protocol V2 - Python library and CLI
Rotation- and scale-invariant shape matching for machine vision — fast C++ core, simple Python API
Easily computing clip embeddings and building a clip retrieval system with them
High-performance ML data loading: C++20 core with SIMD-accelerated transforms, pipe-operator composition, TBL v2 format, and a PyTorch-compatible DataLoader.
Understand unfamiliar ML notebooks with evidence-backed explanations inside Jupyter, without LLMs.
Anomaly detection for machine vision — train from good images only, structural and logical defects, with a dashboard
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
Neo MCP server — bring Neo, the autonomous AI engineer for ML, LLM, GenAI & data workflows, into Claude Code, Cursor, Codex & other editors. Describe a task; Neo builds it and writes results to your repo.
A research and production integrated edge-cloud library for federated/distributed machine learning at anywhere at any scale.
A Model-Agnostic Metamorphic Testing Framework for Regression-Based AI/ML Models with High-Performance Parallel Validation
No-code neural network studio in your terminal: build, train, fine-tune and export PyTorch models.
[DEPRECATED] An inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application
Smart image downsampling for image classification datasets
This is the module for detecting and classifying text on rama pictures
[DEPRECATED] Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes
[DEPRECATED] Easy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint
[DEPRECATED] Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
Eyes for AI Agents — a machine-graded visual feedback loop coding agents consume to self-correct before claiming done.
AbleVLabs tools: kami, a machine-learning tutor that builds models and explains them in plain English, now including a PyTorch half that trains a network for you, shows you the code it ran, and reads the training loop you wrote yourself; lana, a weighted record-comparison engine that weighs records attribute by attribute and tells you which wins; and agoge, a resistance-training coach that estimates reps in reserve and tracks fatigue, powered by the Vivanco Proximity-to-Failure Model.
Machine vision inspection platform for production lines
A package designed to predict static pose and detect falls with 2D RGB Camera in well lit indoor environments.
The Astromech arm for your Python data projects — end-to-end ML toolkit
Sign Language Toolkit for sign language research
A powerful NSFW content detection library using EVA-based vision transformer
A rastervision plugin that adds geospatial machine learning pipelines
A Python library including general functions and operations on various computer vision related structures.
Pymba is a Python wrapper for Allied Vision's Vimba C API.
Turn imagery and labels into ready-to-train remote-sensing datasets, fast.
ML/DL tools function library