AI2-THOR: A Near Photo-Realistic Interactable Framework for Embodied AI Agents
An inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application
Python utilities for computer vision
OpenMMLab Model Deployment
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.
OpenMMLab Computer Vision Foundation
OpenMMLab Video Understanding Toolbox and Benchmark
Find issues in image datasets
OpenMMLab's next-generation platformfor general 3D object detection.
CLIP (Contrastive Language-Image Pre-Training) is a neural network trained on a variety of (image, text) pairs. It can be instructed in natural language to predict the most relevant text snippet, given an image, without directly optimizing for the task, similarly to the zero-shot capabilities of GPT-2 and 3. We found CLIP matches the performance of the original ResNet50 on ImageNet “zero-shot” without using any of the original 1.28M labeled examples, overcoming several major challenges in computer vision.
Tensorflow keras computer vision attention models. Alias kecam. https://github.com/leondgarse/keras_cv_attention_models
Python SDK for Onepanel
cuCIM - an extensible toolkit designed to provide GPU accelerated I/O, computer vision & image processing primitives for N-Dimensional images with a focus on biomedical imaging.
An inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application
A lightweight Computer Vision library for high-performance AI research - Modern Computer Vision on the Fly.
Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes
A python library built to empower developers to build applications and systems with self-contained Computer Vision capabilities
Extract tables from PDFs
A simple, high level, easy to use, open source computer vision library for python
Conversions between kornia and other computer vision libraries formats
Fast symbolic computation, code generation, and nonlinear optimization for robotics
Easily computing clip embeddings and building a clip retrieval system with them
Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes
OpenVINO™ Training Extensions: Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™
🔥LIT: The Learning Interpretability Tool
Pymba is a Python wrapper for Allied Vision's Vimba C API.
Differentiable rendering without approximation.
AI-Powered Command-Line Photo Search Tool
Declarative machine learning: End-to-end machine learning pipelines using data-driven configurations.
Easy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint
Transform, analyze, and visualize computer vision annotations.
Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
Utilities for computer vision and 3D geometry
Agnostic Computer Vision Framework
equirectangular image processing with python using minimum dependencies
OpenMMLab Toolbox of YOLO
doc2text drastically improves the extraction of text from images by fixing resolution, text area (crop), and skew.
Visual testing framework. Combining selenium and computer vision.
OpenMMLab Model Deployment SDK python api
Build computer vision applications for the edge quickly and easily.
cuCIM - an extensible toolkit designed to provide GPU accelerated I/O, computer vision & image processing primitives for N-Dimensional images with a focus on biomedical imaging.
TorchSeg: Semantic Segmentation models for PyTorch
OpenMMLab Model Deployment SDK python api
OML is a PyTorch-based framework to train and validate the models producing high-quality embeddings.
Ikomia Python API for Computer Vision workflow and plugin integration in Ikomia Studio
A easy to use huggingface wrapper for computer vision.
Vid2Info is an easy-to-use Computer Vision pipeline that implements Detection, Tracking and, optionally, Segmentation.