Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™

Official implementation of "Align and Distill: Unifying and Improving Domain Adaptive Object Detection"

NetworkOptix open-source components used to build Powered-by-Nx products including Desktop Client for Network Optix Video Management Platform.

Application de détection de bateaux à partir de vues aériennes utilisant Yolov8.

Comparative benchmarks of CNN models for detecting gunshot holes in targets, aiming at identifying top-performing architectures in accuracy and efficiency.

A fast, easy-to-use, production-ready inference server for computer vision supporting deployment of many popular model architectures and fine-tuned models.

A repo designed to convert audio-based "weak" labels to "strong" intraclip labels. Provides a pipeline to compare automated moment-to-moment labels to human labels. Current proof of concept work being fulfilled on Bird Audio clips using Microfaune predictions.

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

Notebooks to upload/download marine footage, connect to a citizen science project, train machine learning models and publish marine biological observations.

Dataset Colab allows FRC teams to collaborate on a large object detection dataset and models.

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

PyTorch implementations of recent Computer Vision tricks (ReXNet, RepVGG, Unet3p, YOLOv4, CIoU loss, AdaBelief, PolyLoss, MobileOne)

deep learning for image processing including classification and object-detection etc.

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

Testing harness is an integrated dashboard to evaluate the capabilities of various LLM models

We write your reusable computer vision tools. 💜

NVR with realtime local object detection for IP cameras

Deploy Computer Vision solutions with a few lines of code.

📸 A robust image classifier and object detector tailored for photographers. Harnessing the power of Vision Transformer (ViT) and DEtection TRansformer (DETR), this app brings AI-driven insights to your photos. 🚀