A set of type stubs for popular Python packages. These are works in progress from the Microsoft Python team and others, with the intent that they are contributed to typeshed or to the associated packages once sufficiently complete.
Обновлено 2024-11-08 02:58:16 +03:00
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Обновлено 2024-11-07 07:38:21 +03:00
The Microsoft Bot Framework provides what you need to build and connect intelligent bots that interact naturally wherever your users are talking, from text/sms to Skype, Slack, Office 365 mail and other popular services.
Обновлено 2024-11-04 12:14:35 +03:00
Loader for different .NET runtimes
Обновлено 2024-09-04 01:52:41 +03:00
This is an official Pytorch implementation of "Cross View Fusion for 3D Human Pose Estimation, ICCV 2019".
Обновлено 2024-08-31 02:46:56 +03:00
More efficient exploration for reinforcement learning in two-player, zero-sum game
Обновлено 2024-07-31 00:31:19 +03:00
A research project for natural language generation, containing the official implementations by MSRA NLC team.
Обновлено 2024-07-25 14:27:07 +03:00
An official implementation for " UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation"
Обновлено 2024-07-25 14:07:31 +03:00
Official repository for our NeurIPS 2021 paper "Unadversarial Examples: Designing Objects for Robust Vision"
Обновлено 2024-07-25 14:04:47 +03:00
This is a collection of our NAS and Vision Transformer work.
Обновлено 2024-07-25 13:29:13 +03:00
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Обновлено 2024-07-15 18:00:32 +03:00
XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale
Обновлено 2023-12-20 23:40:01 +03:00
This project provides an official implementation of our recent work on real-time multi-object tracking in videos. The previous works conduct object detection and tracking with two separate models so they are very slow. In contrast, we propose a one-stage solution which does detection and tracking with a single network by elegantly solving the alignment problem. The resulting approach achieves groundbreaking results in terms of both accuracy and speed: (1) it ranks first among all the trackers on the MOT challenges; (2) it is significantly faster than the previous state-of-the-arts. In addition, it scales gracefully to handle a large number of objects.
Обновлено 2023-10-04 00:42:58 +03:00
Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS evaluation metric.
Обновлено 2023-09-07 07:38:34 +03:00
EsViT: Efficient self-supervised Vision Transformers
Обновлено 2023-08-28 04:38:18 +03:00
Official implementation of "VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment"
Обновлено 2023-07-24 03:45:42 +03:00
Official repository for our NeurIPS 2020 *oral* "Do Adversarially Robust ImageNet Models Transfer Better?"
Обновлено 2023-07-07 09:32:07 +03:00
This contains a command line tool, "WopiValidatorExecutor" that uses OfficeOnline's WopiTest application to execute tests which verify the target host's WOPI implementation.
Обновлено 2023-06-27 16:07:16 +03:00
Code for paper EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE
Обновлено 2023-06-12 21:56:30 +03:00
Code for the neural architecture search methods contained in the paper Efficient Forward Neural Architecture Search
Обновлено 2023-06-12 21:22:32 +03:00
Record-and-replay tools are indispensable for quality assurance of mobile applications. However, by conducting an empirical study of various existing tools in industrial settings, researchers have concluded that no existing tools under evaluation are sufficient for industrial applications. In this project, we present a record-and-replay tool called SARA towards bridging the gap and targeting a wide adoption.
Обновлено 2023-06-12 21:21:33 +03:00
Official Implementation of "A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining""
Обновлено 2023-06-12 21:16:08 +03:00
Office 365 Video XBlock for Open edX
Обновлено 2022-11-28 22:13:05 +03:00
The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"
Обновлено 2022-11-28 22:11:04 +03:00
Official Implementation of "DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization."
Обновлено 2022-11-01 10:25:58 +03:00
This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".
Обновлено 2022-09-29 18:17:40 +03:00
An efficient implementation of the popular sequence models for text generation, summarization, and translation tasks. https://arxiv.org/pdf/2106.04718.pdf
Обновлено 2022-08-17 19:38:06 +03:00
Official code for achieving human parity on CommonsenseQA with External Attention
Обновлено 2022-08-11 10:33:51 +03:00
The official Sublime Text package for Go build system integration.
Обновлено 2022-07-22 18:52:51 +03:00
This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.
Обновлено 2022-06-22 07:21:09 +03:00