Microsoft

Repositories

• AI

  Microsoft AI
  Python MIT 53 154 0 0 Updated Jun 12, 2020

• nni

  An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

  python data-science machine-learning deep-learning neural-network tensorflow machine-learning-algorithms
  Python MIT 834 6,274 165 (11 issues need help) 16 Updated Jun 12, 2020

• unilm

  UniLM - Unified Language Model Pre-training / Pre-training for NLP and Beyond

  nlp language-generation language-understanding pre-trained-model document-understanding unilm minilm
  Python MIT 233 1,124 22 6 Updated Jun 12, 2020

• DeepSpeed

  DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

  machine-learning deep-learning gpu pytorch data-parallelism model-parallelism billion-parameters
  Python MIT 225 2,623 19 6 Updated Jun 12, 2020

• hummingbird

  Hummingbird compiles trained ML models into tensor computation for faster inference.

  machine-learning scikit-learn pytorch neural-networks tensor-computation
  Python MIT 83 1,048 18 (1 issue needs help) 3 Updated Jun 12, 2020

• ExperimentTools

  XTlib is an API and command line tool for scaling and managing ML experiments. The goal of XTLib is to enable you to effortlessly organize and scale your ML experiments. Our tools offer an incremental approach to adoption, so you can begin realizing benefits immediately..
  Python MIT 0 1 0 1 Updated Jun 12, 2020

• onnxconverter-common

  Common utilities for ONNX converters

  machine-learning python-library onnx
  Python MIT 11 27 0 0 Updated Jun 12, 2020

• ptgnn

  A PyTorch Graph Neural Network Library

  deep-learning pytorch geometric-deep-learning graph-neural-networks gnn
  Python MIT 6 66 0 0 Updated Jun 11, 2020

• DeepSpeedExamples

  Example models using DeepSpeed
  Python MIT 8 42 4 0 Updated Jun 11, 2020

• DisentangledFaceGAN

  Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning (CVPR 2020 Oral)
  Python MIT 11 82 1 0 Updated Jun 11, 2020

• Deep3DFaceReconstruction

  Deep3DFaceReconstruction
  Python MIT 132 520 37 0 Updated Jun 11, 2020

• MPNet

  MPNet: Masked and Permuted Pre-training for Language Understanding https://arxiv.org/pdf/2004.09297.pdf
  Python MIT 11 92 0 0 Updated Jun 11, 2020

• pypi-ado-release

  Simple repository with ADO pipeline for PyPI Releases
  Python MIT 0 0 0 0 Updated Jun 11, 2020

• nlp-recipes

  Natural Language Processing Best Practices & Examples

  nlp machine-learning natural-language-processing deep-learning text-classification text best-practices
  Python MIT 625 4,872 45 2 Updated Jun 11, 2020

• MMdnn

  MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

  visualization caffe mxnet cntk tensorflow keras pytorch
  Python MIT 888 4,739 274 (6 issues need help) 7 Updated Jun 11, 2020

• MLOpsPython

  MLOps using Azure ML Services and Azure DevOps

  azure-machine-learning azureml mlops
  Python MIT 355 299 28 4 Updated Jun 11, 2020

• TextWorld

  ​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

  reinforcement-learning text-based-adventure text-based-game
  Python 128 817 10 7 Updated Jun 11, 2020

• ProphetNet

  ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training https://arxiv.org/pdf/2001.04063.pdf
  Python MIT 23 115 10 0 Updated Jun 10, 2020

• msticnb

  MSTIC Notebook Components
  Python MIT 0 3 0 1 Updated Jun 11, 2020

• TREC-2019-Deep-Learning

  Website for the TREC Deep Learning Track 2019
  Python 15 71 0 0 Updated Jun 10, 2020

• seismic-deeplearning

  Deep Learning for Seismic Imaging and Interpretation

  microsoft computer-vision deep-learning neural-networks segmentation seismic seismic-inversion
  Python MIT 42 118 65 3 Updated Jun 12, 2020

• dowhy

  DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.

  data-science machine-learning python3 graphical-models bayesian-networks causal-inference
  Python MIT 269 1,980 7 (1 issue needs help) 1 Updated Jun 10, 2020

• MLOps_VideoAnomalyDetection

  Operationalize a video anomaly detection model with Azure ML

  azureml mlops
  Python MIT 32 64 0 1 Updated Jun 10, 2020

• msticpy

  Microsoft Threat Intelligence Security Tools
  Python MIT 42 291 1 2 Updated Jun 12, 2020

• debugpy

  An implementation of the Debug Adapter Protocol for Python
  Python 9 99 117 1 Updated Jun 9, 2020

• PowerPlatformConnectors

  This is a repository for Microsoft Power Automate, Power Apps, and Azure Logic Apps connectors

  microsoft connector powerapps logicapps powerautomate power-platform
  Python MIT 133 115 14 17 Updated Jun 12, 2020

• AirSim-Drone-Racing-VAE-Imitation

  Code associated with our paper "Learning Visuomotor Policies for Aerial Navigation Using Cross-Modal Representations": https://arxiv.org/abs/1909.06993
  Python MIT 18 52 1 0 Updated Jun 9, 2020

• OLive

  OLive, meaning ONNX go live, integrates model conversion, optimization, correctness test and performance tuning into a single pipeline and outputs a production ready ONNX model with ONNX Runtime configurations (execution provider + optimization options)
  Python MIT 9 75 0 1 Updated Jun 9, 2020

• automl_utils

  Utilities to streamline the creation and evaluation of AutoML algorithms.
  Python 0 0 0 0 Updated Jun 9, 2020

• MT-DNN

  Multi-Task Deep Neural Networks for Natural Language Understanding
  Python MIT 5 30 1 1 Updated Jun 8, 2020