A DNN inference latency prediction toolkit for accurately modeling and predicting the latency on diverse edge devices.
machine-learning
python
deep-learning
pytorch
neural-architecture-search
deep-neural-networks
edge-computing
latency
inference
edge-ai
efficient-model
onnx-models
tensorflow-models
Обновлено 2024-07-31 00:16:53 +03:00
Samples and Tools for Windows ML.
machine-learning
deep-learning
windows
pytorch
ai
ml
tensorflow
scikit-learn
neural-network
onnx
keras
coreml
caffe2
winmltools
Обновлено 2024-05-28 23:28:15 +03:00
This open source project contains source code to build a Xamarin iOS and Android mobile app. Once compiled the app can be used to analyze and interpret chest x-ray images. This experimental research project is used to supplement the release of the machine learning model (https://blogs.technet.microsoft.com/machinelearning/2018/03/07/using-microsoft-ai-to-build-a-lung-disease-prediction-model-using-chest-x-ray-images/).
Обновлено 2024-01-27 23:05:50 +03:00
Samples for getting started with deep learning across TensorFlow, CNTK, Theano and more.
Обновлено 2023-06-27 16:03:51 +03:00
Vision AI Developer Kit Preview
Обновлено 2023-06-02 21:21:54 +03:00
Tailwind Traders Backend Services
Обновлено 2023-03-20 20:41:32 +03:00
MoveBox is a toolbox to animate the Microsoft Rocketbox avatars using motion captured (MoCap). Motion capture is performed using a single depth sensor, such as Azure Kinect or Windows Kinect V2. Our toolbox enables real-time animation of the user's avatar by converting the transformations between systems that have different joints and hierarchies. Additional features of the toolbox include recording, playback and looping animations, as well as basic audio lip sync, blinking and resizing of avatars. Our main contribution is both in the creation of this open source tool as well as the integration of MoveBox with Kinect V2 and Azure Kinect, as well as the interfacing with the Microsoft Rocketbox avatars.
Обновлено 2021-03-26 22:07:07 +03:00