Displaying 1 to 14 from 14 results

onnx - Open Neural Network Exchange

  •    PureBasic

Open Neural Network Exchange (ONNX) is the first step toward an open ecosystem that empowers AI developers to choose the right tools as their project evolves. ONNX provides an open source format for AI models. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types. Initially we focus on the capabilities needed for inferencing (evaluation). Caffe2, PyTorch, Microsoft Cognitive Toolkit, Apache MXNet and other tools are developing ONNX support. Enabling interoperability between different frameworks and streamlining the path from research to production will increase the speed of innovation in the AI community. We are an early stage and we invite the community to submit feedback and help us further evolve ONNX.

deepo - A series of Docker images (and their generator) that allows you to quickly set up your deep learning research environment

  •    Python

If you want to share your data and configurations between the host (your machine or VM) and the container in which you are using Deepo, use the -v option, e.g. This will make /host/data from the host visible as /data in the container, and /host/config as /config. Such isolation reduces the chances of your containerized experiments overwriting or using wrong data.

dlwin - GPU-accelerated Deep Learning on Windows 10 native

  •    Python

There are certainly a lot of guides to assist you build great deep learning (DL) setups on Linux or Mac OS (including with Tensorflow which, unfortunately, as of this posting, cannot be easily installed on Windows), but few care about building an efficient Windows 10-native setup. Most focus on running an Ubuntu VM hosted on Windows or using Docker, unnecessary - and ultimately sub-optimal - steps. We also found enough misguiding/deprecated information out there to make it worthwhile putting together a step-by-step guide for the latest stable versions of Keras, Tensorflow, CNTK, MXNet, and PyTorch. Used either together (e.g., Keras with Tensorflow backend), or independently -- PyTorch cannot be used as a Keras backend, TensorFlow can be used on its own -- they make for some of the most powerful deep learning python libraries to work natively on Windows.

MMdnn - MMdnn is a set of tools to help users inter-operate among different deep learning frameworks

  •    Python

A comprehensive, cross-framework solution to convert, visualize and diagnosis deep neural network models. The "MM" in MMdnn stands for model management and "dnn" is an acronym for deep neural network.Across the industry and academia, there are a number of existing frameworks available for developers and researchers to design a model, where each framework has its own network structure definition and saving model format. The gaps between frameworks impede the inter-operation of the models.




MMLSpark - Microsoft Machine Learning for Apache Spark

  •    Scala

MMLSpark provides a number of deep learning and data science tools for Apache Spark, including seamless integration of Spark Machine Learning pipelines with Microsoft Cognitive Toolkit (CNTK) and OpenCV, enabling you to quickly create powerful, highly-scalable predictive and analytical models for large image and text datasets.MMLSpark requires Scala 2.11, Spark 2.1+, and either Python 2.7 or Python 3.5+. See the API documentation for Scala and for PySpark.

keras-rcnn - Keras package for region-based convolutional neural networks (RCNNs)

  •    Python

keras-rcnn is the Keras package for region-based convolutional neural networks. The data is made up of a list of dictionaries corresponding to images.

AutonomousDrivingCookbook - Scenarios, tutorials and demos for Autonomous Driving

  •    Jupyter

This project is developed and being maintained by the Microsoft Deep Learning and Robotics Garage Chapter. This is currently a work in progress. We will continue to add more tutorials and scenarios based on requests from our users and the availability of our collaborators.Autonomous Driving has transcended far beyond being a crazy moonshot idea over the last half decade or so. It is quickly becoming the biggest technology today that promises to shape our tomorrow, not very unlike when cars came into existence in the first place. Almost every single car manufacturer, every big technology company, and a number of very promising startups have been working on different aspects of autonomous driving to help shape this revolution. Some of the biggest drivers powering this change have been the recent advances in software (robotics and deep learning techniques), hardware technology (GPUs, FPGAs etc.) and cloud computing. Cloud platforms like Azure have enabled ingest and processing of large amounts of data, making it possible for companies to push for levels 4 and 5 of AD autonomy.

CNTK-FastRCNNDetector - A python implementation for a CNTK Fast-RCNN evaluation client

  •    Python

A python implementation for a CNTK Fast-RCNN evaluation client.Call a Fast-RCNN python model from your python code, or run as a script directly from the command line.


VoTT - Visual Object Tagging Tool: An electron app for building end to end Object Detection Models from Images and Videos

  •    Javascript

This tool provides end to end support for generating datasets and validating object detection models from video and image assets.Run the app by launching the "VOTT" executable which will be located inside the unzipped folder.

azure-toolbox - A Docker container with Azure Resource Manager administration tools and a machine/deep learning stack

  •    Makefile

No need to use SSH, no VNC authentication. Great for trying it out -- but a bad idea if you expose Docker ports outside your machine. If you're using a Mac, then don't use noauth and type changeme as a VNC password (the built-in VNC client rightfully dislikes null authentication options).

cntk-fully-convolutional-networks - CNTK implementation of Fully Convolutional Networks (FCN) with ResNet for semantic segmentation

  •    Jupyter

This is a CNTK implementation of Fully Convolutional Network, which is a deep learning segmentation method proposed by J. Long et al. The FCN was originally proposed using VGG, but here we use ResNet-18 as the base model.

cntk_unet - CNTK implementation of U-Net for image segmentation

  •    Jupyter

This is a CNTK implementation of U-net, which is a deep learning segmentation method proposed by Ronneberger et al.

pydata-medical-image - A Deep Learning talk+tutorial for medical image processing

  •    Jupyter

This repository is for storing scripts/notebooks for "Medical image processing using Microsoft Deep Learning framework (CNTK)" (https://pydata.org/seattle2017/schedule/presentation/94/). The presentation slide is available here.

pixel_level_land_classification - Tutorial demonstrating how to create a semantic segmentation (pixel-level classification) model to predict land cover from aerial imagery

  •    Jupyter

This repository contains a tutorial illustrating how to create a deep neural network model that accepts an aerial image as input and returns a land cover label (forested, water, etc.) for every pixel in the image. Microsoft's Cognitive Toolkit (CNTK) is used to train and evaluate the model on an Azure Geo AI Data Science Virtual Machine or an Azure Batch AI GPU cluster. The method shown here was developed in collaboration between the Chesapeake Conservancy, ESRI, and Microsoft Research as part of Microsoft's AI for Earth initiative. We recommend budgeting two hours for a full walkthrough of this tutorial. The code, shell commands, trained models, and sample images provided here may prove helpful even if you prefer not to complete the walkthrough: we have provided explanations and direct links to these materials where possible.