happynaruto
Follow
Stars
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
Llama中文社区，Llama3在线体验和微调模型已开放，实时汇总最新Llama3学习资料，已将所有代码更新适配Llama3，构建最好的中文Llama大模型，完全开源可商用
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。
A visual no-code/code-free web crawler/spider易采集：一个可视化浏览器自动化测试/数据采集/爬虫软件，可以无代码图形化的设计和执行爬虫任务。别名：ServiceWrapper面向Web应用的智能化服务封装系统。
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐
This is an unofficial implementation for the 2019 ICCV paper 'Decorrelated Adversarial Learning for Age-Invariant Face Recognition' from Tencent AI Lab
[CVPR2021] Invertible Image Signal Processing
NR and FR IQA models based on Deep Convolutional Neural Networks
Google Research
Unofficial Implementation of ICCV 2021 paper titled "Light Source Guided Single-Image Flare Removal from Unpaired Data"
PyTorch Implementation of "How to Train Neural Networks for Flare Removal"
This is the code for "Multi-Exposure Image Fusion via Deep Perceptual Enhancement".
Learning a Deep Single Image Contrast Enhancer from Multi-Exposure Images (TIP 2018)
Project page of the paper "Learning Multi-Scale Photo Exposure Correction" (CVPR 2021).
Tech report for Multi-Exposure Fusion
Perceptual video quality assessment based on multi-method fusion.
GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment
Pytorch code for our AAAI2022 Oral paper "Content-Variant Reference Image Quality Assessment via Knowledge Distillation"
喵币助手：年货节天猫（淘宝）、京东任务一键完成。基于AutoX.JS。
Official Matlab Code of Paper "Structure-Texture Image Decomposition Using Discriminative Patch Recurrence"
No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency
Unofficial implementation of CVPR2021 paper "Perceptual Image Quality Assessment with Transformers"
deep learning for image processing including classification and object-detection etc.
Summary of related papers on visual attention. Related code will be released based on Jittor gradually.
[ICCV'21] CKDN: Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment