Lightning-fast serving engine for any AI model of any size. Flexible. Easy. Enterprise-scale.

An open-source framework for training large multimodal models.

Represent, send, store and search multimodal data

深度学习经典、新论文逐段精读

A Unified Library for Parameter-Efficient and Modular Transfer Learning

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.

全国各省市停贷通知汇总

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

Free Google Translator API 免费的Google翻译

🌐 Google 翻译 Mac 客户端

A curated list of awesome papers related to pre-trained models for information retrieval (a.k.a., pretraining for IR).

Repo for external large-scale work

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

Azure HPC/AI VM Images

A data augmentations library for audio, image, text, and video.

一个多模态内容理解算法框架，其中包含数据处理、预训练模型、常见模型以及模型加速等模块。

Recent Advances in Vision and Language PreTrained Models (VL-PTMs)

Run upstream VS Code on a remote machine with access through a modern web browser from any device, anywhere.

VS Code in the browser

Bridging Vision and Language Model

This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.

Reading list for research topics in multimodal machine learning

我终于能用谷歌搜中文了……

A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]

CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection

Use the browser's online image format converter, no need to upload files, you can convert jpeg, jpg, png, gif, webp, svg, ico, bmp files to jpeg, png, webp animation, gif, base64,avif,mozjpeg. 使用浏览…

Official implementation of "VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment"

中国提供计算机视觉(CV)算法岗位的公司名单，欢迎大家提交issues进行补充