VITA-Alchemy

MASR

Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。

edgeyolo

an edge-real-time anchor-free object detector with decent performance

CodeFormer

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

speechbrain

A PyTorch-based Speech Toolkit

ColossalAI

Making large AI models cheaper, faster and more accessible

PaddleNLP

👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis etc.

PaddleLabel

飞桨智能标注，让标注快人一步

PaddleSpeech

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit

ETH-XGaze

Official implementation of ETH-XGaze dataset baseline

TransCrowd

[SCIS] TransCrowd: Weakly-Supervised Crowd Counting with Transformers

CrowdCounting-P2PNet

The official codes for the ICCV2021 Oral presentation "Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework"

Bayesian-Crowd-Counting

Official Implement of ICCV 2019 oral paper Bayesian Loss for Crowd Count Estimation with Point Supervision

Detection

基于视频的行人流量密度检测

Ultra-Fast-Lane-Detection-v2

Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification (TPAMI 2022)

kapao

KAPAO is an efficient single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.

edgeai-yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite. Forked from https://ultralytics.com/yolov5

AWNet-Attentive-Wavelet-Network-for-Image-ISP

Runner-Up solution in AIM 2020 Learned Image ISP challenge (ECCVW 2020)

PyNET

Generating RGB photos from RAW image files with PyNET

CV-CUDA

CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

kubeedge

Kubernetes Native Edge Computing Framework (project under CNCF)

WasmEdge

WasmEdge is a lightweight, high-performance, and extensible WebAssembly runtime for cloud native, edge, and decentralized applications. It powers serverless apps, embedded functions, microservices, smart contracts, and IoT devices.

k3s

Lightweight Kubernetes

ultralytics

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

object-detection-augmentation

这里面存放了一些目标检测算法的数据增强方法。如mosaic、mixup。

vue-webassembly-ncnn

annotorious

Add image annotation functionality to any web page with a few lines of JavaScript.

codon

A high-performance, zero-overhead, extensible Python compiler using LLVM

nvitop

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

triton

Development repository for the Triton language and compiler