Stars
基于AI的图片/视频硬字幕去除、文本水印去除,无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API,本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
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。
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
AutoML for image augmentation. AutoAlbument uses the Faster AutoAugment algorithm to find optimal augmentation policies. Documentation - https://albumentations.ai/docs/autoalbument/
Provide best practices for LMOps, as well as elegant and convenient access to the features of the Qianfan MaaS Platform. (提供大模型工具链最佳实践,以及优雅且便捷地访问千帆大模型平台)
StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.
TensorFlow implementation of the CVPR 2018 spotlight paper, Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs
A collection of state-of-the-art image quality assessment algorithms
🖼️ 𝖀𝖓𝖔𝖋𝖋𝖎𝖈𝖎𝖆𝖑 PyTorch implementation of "Learning Fine-grained Image Similarity with Deep Ranking" (arXiv:1404.4661)
Code and website for DAL (Discriminative Active Learning) - a new active learning algorithm for neural networks in the batch setting. For the blog:
The repo covers some widely used relation extraction datasets and will be continuously updated.
keras implement of transformers for humans
The source code and dataset for our paper "Integrating Relation Constraints with Neural Relation Extractors" which is publicated at AAAI 2020
[ACL 2020] A Novel Cascade Binary Tagging Framework for Relational Triple Extraction
翻墙-科学上网、自由上网、免费科学上网、免费翻墙、fanqiang、油管youtube/视频下载、软件、VPN、一键翻墙浏览器,vps一键搭建翻墙服务器脚本/教程,免费shadowsocks/ss/ssr/v2ray/goflyway账号/节点,翻墙梯子,电脑、手机、iOS、安卓、windows、Mac、Linux、路由器翻墙、科学上网、youtube视频下载、youtube油管镜像/免翻墙…