kevinfu1717 Goto Github PK

followers: 6.0 following: 4.0 repos: 38.0 gists: 0.0

Name: 符志成 Kevin

Type: User

Company: D&E

Location: GZ

符志成 Kevin's Projects

3dpointsfittoplane

Fit 3D points to a plane base on serval methods:SVD,PCA,NN(base on PaddlePaddle2.0+)

🔥🔥AidLearning is a powerful mobile development platform, AidLearning builds a linux env supporting GUI, deep learning and visual IDE on Android...Now Aid supports OpenCL (GPU+NPU) for high performance acceleration...Linux on Android or HarmonyOS

aidluxsmartassistant

制作一个完全自己说了算的智能音箱

airsim

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

autopy

A simple, cross-platform GUI automation module for Python and Rust.

backgroundmattingv2

Real-Time High-Resolution Background Matting

childrenstoryforeducation

LLM generate children story with a given theme and a page of a picture book.上传儿童正在看的绘本中任意一页，程序将该页所画的角色作为故事的主角，父母可以定义一些提醒或好习惯作为故事主题，创作个性化的故事。Edge浏览器访问后即可朗读出来，无需下载其他app，方便易用。

chmsearch

一个下载即用的聚合搜索网页。

deepfacelive

Real-time face swap for PC streaming or video calls

flask-video-streaming

Supporting code for my article on video streaming with Flask.

foolnltk

A Chinese Nature Language Toolkit

frigate

NVR with realtime local object detection for IP cameras

glide-text2im

GLIDE: a diffusion-based text-conditional image synthesis model

logging2feishu

Sync the print in python to the Feishu multidimensional spreadsheet. You can view the running log of a script in real time. It is convenient for AI trainers or AI painters to check the training situation of the model or LORA, etc. during the refining process, and can immediately stop or modify and retrain, without having to stay in front of PC

min-dalle

min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch

minigpt-4

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

mixpoet

Source codes of MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space (AAAI 2020)

multimediachatbot

构建了可用于多个对话框架的场景型对话的聊天机器人。支持吐槽类情景及情感倾诉型情景。使用wechaty，结合Paddlehub的人脸特征点、动漫人脸生成、对联生成、情感分类，ernie迁移，人脸变胖

openvino

OpenVINO™ Toolkit repository

openvino-paddlepaddle-demo

This repository provides examples of PaddlePaddle and OpenVINO integration.

paddle-image-models

A PaddlePaddle version image model zoo.

paddlegan

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.

paddlehub

Awesome pre-trained models toolkit based on PaddlePaddle.(300+ models including Image, Text, Audio and Video with Easy Inference & Serving deployment)

playpianoontablebyhandpose

利用3d hand pose keypoint的手部21关键点模型进行指尖位置识别，pygame用作画面显示，ui互动，钢琴声音播放，让我们可以在桌上弹钢琴

porcupine

On-device wake word detection powered by deep learning

pyhikvision

hikvision-sdk for Python3 in action

rasa_ch_faq

用 rasa 实现 rasa demo 机器人，有一些惊奇的功能，faq，图谱，多轮等

retrieval-based-voice-conversion-webui

Voice data <= 10 mins can also be used to train a good VC model!

sand-painting

把普通图片或照片转成沙画。基于paddlehub的msgnet进行迁移学习。固定freeze backbone的参数来transfer learning。

kevinfu1717 Goto Github PK

符志成 Kevin's Projects

Recommend Projects

Recommend Topics

Recommend Org