pass-o-guava Goto Github PK

a-drawio

ai.js

Based on the @xenova/transformers and @mediapipe/tasks-vision, this project provides code for open-set object detection and speech translation.

alphapose

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

chatglm-6b-int4-qe

chinese-clip

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

chineseocr_lite

超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

cn-clips-retriever

Chinese CLIP Models for Image-Text Retrieval

cyclegan

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

deep-high-resolution-net.pytorch

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

facedetection-dsfd

腾讯优图高精度双分支人脸检测器

mmskeleton

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

mysql-sandbox

Quick and painless install of one or more MySQL servers in the same host.

nanodet

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

objectdetection

TensorFlow Object Detection Demo

openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

pytorch_blazeface

Unofficial PyTorch implementation of BlazeFace

pytorch_retinaface

Retinaface get 80.99% in widerface hard val using mobilenet0.25.

semiot-platform

SemIoT Platform

smartroomv2

Struts+Rest+Jena+Mybatis+[Arduino]

stablediffusion-demo

stablediffusionunipipeline

Stable diffusion txt2img and img2img pipeline merging and GPU parallel acceleration based on diffusers

tensorflow

Computation using data flow graphs for scalable machine learning

tf-pose-estimation

Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.

videopose

3D pose estimation for wild videos， embed 2d keypoints detector like hrnet alphapose and openpose

videopose3d

Efficient 3D human pose estimation in video using 2D keypoint trajectories

webprotege

The webprotege code base

yolov5s-compression