Lightweight tensorflow and keras that can be deployed to Lambda

A dataset of images for artificial intelligence models to recognize human actions.

A DeepStack custom model for detecting common objects in dark/night images and videos.

A deep learning model for detecting fire in video and camera streams

A dataset of traffic, fire and accident images for training deep learning models.

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

IdenProf dataset is a collection of images of identifiable professionals. It is been collected to enable the development of AI systems that can serve by identifying people and the nature of their j…

Detect and blur faces with OpenCV.

The only Kubernetes dashboard you need

Hermes is a Wildfire detection system that utilizes Computer Vision and is accelerated using NVIDIA Deepstream

Portal is the fastest way to load and visualize your deep neural networks on images and videos 🔮

Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that this is only good for course demo, not for real world applications !!! Those ary very difficult !!!)

PyTorch training code for FastSeg: https://github.com/ekzhang/fastseg

🔥 作者：常炎隆(Author: ChangYanlong):HEVC/H.265 网页直播/点播播放器 支持硬解！ 支持H.265的HttpFLV/HLS/MP4/TS/FLV/M3U8/Websocket播放。 🔥 A HEVC/H.265 Web Player, Support hard-decoding! for LIVE/VOD stream. Support H.265 Code…

An example of using FFmpeg.wasm to perform streaming transcoding within the browser

COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning

A video.js plugin to display simple overlays during playback.

A player to rotate and zoom videos in HTML5

VideoFrame - HTML5 Video SMPTE Time Code and Frame Seeking API

This sample shows how to train and deploy a deep learning model for the real time redaction of faces from video streams using the NVIDIA DeepStream SDK

"Automatically Discovering and Learning New Visual Categories with Ranking Statistics" by Kai Han, Sylvestre-Alvise Rebuffi, Sebastien Ehrhardt, Andrea Vedaldi, Andrew Zisserman (ICLR 2020)

Face2Data: Extract meaningful information from a person face in less than a second. Powered by Keras and Flask.

Opencv HDR demo

New generated dataset for fight detection in surveillance cameras.

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

code for my BlogPost. Uses ML5.js and P5.js to run poseNet in browser with webcam

Robotics with GPU computing

YOLOv3 in PyTorch > ONNX > CoreML > TFLite