tabsun

OpenCV-Face-Recognition

Real-time face recognition project with OpenCV and Python

yolov8-face-landmarks-opencv-dnn

使用OpenCV部署yolov8检测人脸和关键点以及人脸质量评价，包含C++和Python两个版本的程序，只依赖opencv库就可以运行，彻底摆脱对任何深度学习框架的依赖。

sam2

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

ARTrack

YOWOF

You Only Watch One Frame for Online Spatio-Temporal Action Detection

YOWO

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization

AnimateDiff

Official implementation of AnimateDiff.

generative-models

Generative Models by Stability AI

kinetics-i3d

Convolutional neural network model for video classification trained on the Kinetics dataset.

actionformer_release

Code release for ActionFormer (ECCV 2022)

hiera

Hiera: A fast, powerful, and simple hierarchical vision transformer.

DiffusionVID

Official Repository of the paper "DiffusionVID: Denoising Object Boxes with Spatio-temporal Conditioning for Video Object Detection"

ComfyUI-DepthAnythingV2

Simple DepthAnythingV2 inference node for monocular depth estimation

yolov5ByteTrack

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

ultralytics

Ultralytics YOLO11 🚀

Machine-Learning-Interviews

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

ToDistribute

Bilibili-Downloader-Cli

一个轻量的b站下载器,支持下载B站视频,番剧,电影,电视剧等

OpenVoice

Instant voice cloning by MIT and MyShell.

TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

SEINE

[ICLR 2024] SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

Crosstalk-Generation

Perform crosstalk with Qian Yu

live_sketch

latent-consistency-model

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Chinese-CLIP

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

RT-DETR

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

PaddleDetection

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

awesome_LLMs_interview_notes

LLMs interview notes and answers:该仓库主要记录大模型（LLMs）算法工程师相关的面试题和参考答案

Tip-Adapter

PromptDet

PromptDet: Towards Open-vocabulary Detection using Uncurated Images, ECCV2022