liuheng0111

AdelaiDet

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

AiLearning

AiLearning: 机器学习 - MachineLearning - ML、深度学习 - DeepLearning - DL、自然语言处理 NLP

alpaca-lora

Instruct-tune LLaMA on consumer hardware

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.

benchmark-milvus

benchmark tests for milvus

big-ann-benchmarks

Framework for evaluating ANNS algorithms on billion scale datasets.

chineseocr_lite

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

ClassyVision

An end-to-end PyTorch framework for image and video classification

cs344

Introduction to Parallel Programming class code

DALI

A library containing both highly optimized building blocks and an execution engine for data pre-processing in deep learning applications

DiskANN

Graph based indices for approximate nearest neighbor search

google-research

Google Research

havenask

HyperLPR

基于深度学习高性能中文车牌识别 High Performance Chinese License Plate Recognition Framework.

kmeans_pytorch

kmeans using PyTorch

LLaVA

Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.

LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

MaskTextSpotterV3

The code of "Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting"

OCR_ICDAR_label_revise

PaddleOCR

Awesome OCR toolkits based on PaddlePaddle （3.5M practical ultra lightweight OCR system, support training and deployment among server, mobile, embedded and IoT devices）

paddlepaddle_param_to_pyotrch

将mobilenetv3_small的paddlepaddle参数转换为pytorch的模型参数

PandaOCR

PandaOCR - 多功能OCR图文识别+翻译+朗读+弹窗+公式+表格+图床+搜图+二维码

Product1M

Product1M

PyRetri

Open source deep learning based unsupervised image retrieval toolbox built on PyTorch🔥

PytorchOCR

基于Pytorch的OCR工具库，支持常用的文字检测和识别算法

SynthText

Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016.

text_renderer

Generate text images for training deep learning ocr model

TNN

TNN：由腾讯优图实验室打造，移动端高性能、轻量级推理框架，同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。TNN框架在原有Rapidnet、ncnn框架的基础上进一步加强了移动端设备的支持以及性能优化，同时也借鉴了业界主流开源框架高性能和良好拓展性的优点。目前TNN已经在手Q、微视、P图等应用中落地，欢迎大家参与协同共建，促进TNN推理框架进一步完善。

UnrealText

Synthetic Scene Text from 3D Engines

warp-ctc

Fast parallel CTC.