Microsoft

Open source projects and samples from Microsoft

Compiler with automatic differentiation
Обновлено 2023-10-18 04:51:14 +03:00
WMG agent
Обновлено 2023-10-04 02:33:18 +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
Toolkit for building machine learning models that generalize to unseen domains and are robust to privacy and other attacks.
Обновлено 2023-10-03 07:31:52 +03:00
A GA4GH Task Execution Service (TES) compatible implementation for Azure Compute
Обновлено 2023-09-29 18:05:54 +03:00
A collection of Python Packages for AI usecases
Обновлено 2023-09-13 16:34:19 +03:00
Knowledge Computing group - MSRA
Обновлено 2023-09-07 10:20:49 +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
Обновлено 2023-09-01 21:01:04 +03:00
EsViT: Efficient self-supervised Vision Transformers
Обновлено 2023-08-28 04:38:18 +03:00
Oscar and VinVL
Обновлено 2023-08-28 04:34:58 +03:00
A framework for drone racing research, built on Microsoft AirSim.
Обновлено 2023-08-15 00:51:00 +03:00
Visuomotor policies from event-based cameras through representation learning and reinforcement learning. Accompanies our paper: https://arxiv.org/abs/2103.00806
Обновлено 2023-08-15 00:50:21 +03:00
Обновлено 2023-08-15 00:49:53 +03:00
A flexible framework for running experiments with PyTorch models in a simulated Federated Learning (FL) environment.
Обновлено 2023-08-11 23:02:52 +03:00
Code accompanying the paper "Better Exploration with Optimistic Actor Critic" (NeurIPS 2019)
Обновлено 2023-08-11 22:50:02 +03:00
A library & tools to evaluate predictive language models.
Обновлено 2023-08-09 18:22:29 +03:00
ElectionGuard Web API in python to demonstrate usage of electionguard-python in performing ballot encryption, casting, spoiling, and tallying.
Обновлено 2023-08-03 00:11:37 +03:00
ElectionGuard Web API in python to demonstrate usage of electionguard-python in performing ballot encryption, casting, spoiling, and tallying.
Обновлено 2023-08-03 00:11:37 +03:00
A python module implementing the ElectionGuard specification. This implementation can be used to conduct End-to-End Verifiable Elections as well as privacy-enhanced risk-limiting audits.
Обновлено 2023-08-02 03:24:27 +03:00
Azure Command-Line Interface
Обновлено 2023-08-02 02:34:45 +03:00
MonitoFi: Health & Performance Monitor for your Apache NiFi
Обновлено 2023-08-02 02:16:38 +03:00
Обновлено 2023-07-31 17:29:03 +03:00
Benchmark tools for LightGBM
Обновлено 2023-07-28 08:05:03 +03:00
Command line client for Audience Insights
Обновлено 2023-07-27 01:14:55 +03:00
Cosmos Automated Data Exchange Tool 👩‍🚀
Обновлено 2023-07-26 00:00:49 +03:00
Обновлено 2023-07-25 20:34:23 +03:00
Lite Self-Training
Обновлено 2023-07-25 20:31:38 +03:00
Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding (AAAI 2020) - PyTorch Implementation
Обновлено 2023-07-25 19:48:26 +03:00
Token-level Reference-free Hallucination Detection
Обновлено 2023-07-25 19:41:01 +03:00