airhors

sample-notebooks

AI 看新聞

AlphaPose-Yolov8-Yolov5

YOLOv8-Alphapose双流时空图卷积网络

annotated_deep_learning_paper_implementations

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

argoverse-api

Official GitHub repository for Argoverse dataset 多智能體交通預測

Awesome-LLMs-for-Video-Understanding

🔥🔥🔥Latest Papers, Codes and Datasets on Vid-LLMs.

ByteTrack

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

CLIP

請介紹基於文本的視頻搜索大模型

codellama

Inference code for CodeLlama models AI編程

ComfyUI-Florence2

Inference Microsoft Florence2 VLM多任務學習的方式,能夠在視頻理解、圖像-文本匹配等任務上取得良好的結果。

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Devon

Devon: An open-source pair programmer

HybridSORT

[AAAI2024]Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking 遮擋多目標跟蹤

IdealGPT-

Official Code of IdealGPT

MeMOTR

[ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking 有遮擋多目標跟蹤

MetaCLIP

Meta開源基於多顯卡的大模型

MiniGPT4-video

Official code for MiniGPT4-video

Multimodal-Recommendation-with-Large-Vision-Language-Models

mvp-horse-racing-prediction

Using machine learning to predict HK Horse racing results

OpenDevin

🐚 OpenDevin: Code Less, Make More

QCNet

[CVPR 2023] Query-Centric Trajectory Prediction 可能用於賽馬預測

self_llm-automl

基于AutoDL快速部署开源大模型，更适合**宝宝的部署教程

SlowFast

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models. 多目標跟蹤

sn-gamestate

**目標跟蹤

Video-ChatGPT

"Video-ChatGPT" is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.

Video-LLaMA-

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

viper-Python-

Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning"

visprog-

Official code for VisProg (CVPR 2023 Best Paper!)

whisper-clip

用語音找圖

Yolov5_DeepSort_TrackDeepsort-

本文将介绍如何使用yolov5和deepsort进行目标检测和跟踪，并增加轨迹线的显示。本文的改进包括轨迹线颜色与目标框匹配、优化轨迹线只显示一段，并且当目标消失时不显示轨迹线。

yolov9

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information