navyverma
Follow
Stars
Cross-platform .NET/Mono bindings for LibVLC
.NET embeddable video/media player based on mpv for WinForms and WPF
FFME: The Advanced WPF MediaElement (based on FFmpeg)
Which model is the best at object detection? Which is best for small or large objects? We compare the results in a handy leaderboard.
CoTracker is a model for tracking any point (pixel) on a video.
🔥🔥🔥AI-driven database tool and SQL client, The hottest GUI client, supporting MySQL, Oracle, PostgreSQL, DB2, SQL Server, DB2, SQLite, H2, ClickHouse, and more.
Intel® Video Processing Library (Intel® VPL) API, dispatcher, and examples
Official implementation of "Segment Any Anomaly without Training via Hybrid Prompt Regularization (SAA+)".
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜
Fitness Action Quality Assessment or your AI-Fitness Coach [ECCV 2022]
A curated list of software and architecture related design patterns.
Optical Flow Dataset and Benchmark for Visual Crowd Analysis
📚 A curated list of awesome articles, videos, and other resources to learn and practice software architecture, patterns, and principles.
List of useful data augmentation resources. You will find here some not common techniques, libraries, links to GitHub repos, papers, and others.
GStreamer plugins related to the field of machine vision
📊 Simple package for monitoring and control your NVIDIA Jetson [Orin, Xavier, Nano, TX] series
yolov5, yolov8, segmenations, face, pose, keypoints on deepstream
The collection of pre-trained, state-of-the-art AI models for ailia SDK
Largest list of models for Core ML (for iOS 11+)
Notebooks for experimenting with OpenCV
⚡ Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and …
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
A reference system for end to end live streaming video. Capture, encode, package, uplink, origin, CDN, and player.
OpenDataCam proof of concept fork using DeepStream
An open source tool to quantify the world
Data science interview questions and answers