daidaiershidi Goto Github PK

niuke_pachong

nlp-kbqa

opencv

Open Source Computer Vision Library

paddle

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

paddle.js

Paddle.js is a web project for Baidu PaddlePaddle, which is an open source deep learning framework running in the browser. Paddle.js can either load a pre-trained model, or transforming a model from paddle-hub with model transforming tools provided by Paddle.js. It could run in every browser with WebGL/WebGPU/WebAssembly supported. It could also run in Baidu Smartprogram and WX miniprogram.

paddlevideo

Comprehensive, latest, and deployable video deep learning algorithm, including video recognition, action localization, and temporal action detection tasks. It's a high-performance, light-weight codebase provides practical models for video understanding research and application

pyskl

A toolbox for skeleton-based action recognition.

pytorch-project

recognize-anything

Code for the Recognize Anything Model (RAM) and Tag2Text Model

reprod_log

restricted-boltzmann-machines

Restricted Boltzmann Machines in Python.

s-h-esd

Timeseries Anomaly Detection using S-ESD and S-H-ESD

sift_img_splice

Python实现（包括卷积缩放等），拼接用opencv

sinmdm

Single Motion Diffusion Model

summary

拼接生成全景图片：底层实现卷积、sift算法，并通过sift算法找到的关键点实现全景图片。 基于知识库的简易问答系统：使用NLPCC2016KBQA数据集，手动构建NER数据集和SIM数据集，进而实现问答系统。 时序脑波分类：基于SleepEEGNet模型，添加了分型网络的残差结构。 人脸识别：使用的使机器学习算法，底层实现Eigenfaces和Fisherfaces算法实现人脸识别。 手写字母分类：使用的使机器学习算法，底层实现HMM完成手写字母分类。 实时多路存取：底层实现CSMA/CD完成多路存取（带有冲突检测的载波侦听多路存取，是IEEE 802.3使用的一种媒体访问 控制方法）。 机器人应用：基于智元素机器人，实现安卓客户端控制机器人对战和机器人自动搬箱。 简易网页游戏开发：基于游戏引擎Construct3，致敬疫情中的最美逆行者。

t2m-gpt

(CVPR 2023) Pytorch implementation of “T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations”

tadtr

End-to-end Temporal Action Detection with Transformer. [Under review for a journal publication]

temp

1

temp-file

timestampactionseg

timestamp_segmentation

tools

viga-1

"Video Moment Retrieval from Text Queries via Single Frame Annotation" in SIGIR 2022.

vslnet

Span-based Localizing Network for Natural Language Video Localization (ACL 2020)