When multiple services running on the resource-constrained edge devices, how limited resources can dynamically support the desired services is of the utmost importance for both researchers and developers. Efficiently and dynamically managing edge services becomes critical for edge platforms.
I have teamed up with my friends Sharan Babu and Matev to create a Gaze detection system that lets you control your desktop mouse with your eyes. With the help of Openvino we have completed out project.
An open-source classifier programmed using the Intel® Distribution for Python* and trained using Intel® Optimization for TensorFlow*. The model is deployed on a Raspberry 4 using Intel® Distribution of OpenVINO™ Toolkit and inference is carried out using Neural Compute Stick 2.
Security is an important issue for hospitals and medical centers to consider. Today's Facial Recognition can provide ways of automating security in the medical industry, reducing staffing costs and making medical facilities safer for both patients and staff.
During my time as an intern at Intel (Summer 2020), I worked with Health and Life Sciences in the Medical Imaging segment. My project for the summer was to create a demo that runs convolution on medical images on the OneAPI Development Cloud.
Spatter is a new benchmark tool for assessing memory system architectures in the context of a specific category of indexed accesses known as gather and scatter. OneAPI and DevCloud are used to develop support for a OneAPI backend for Spatter that can be targeted to Intel FPGAs.
The vector-multiplication is a simple program that multiplies Three large vectors of integers and verifies the results. This program is implemented using C++ and Data Parallel C++ (DPC++) languages for Intel(R) CPU and accelerators.
In this example, you can learn how to use the most basic code in C
Combining in the right way some Deep Neural Network we can enhance old photos non only restoring them but also improving the resolution and recreating more details.
Face blurring is a computer vision method used to anonymize faces in images and video. In this project, I have used Deep Learning based Face Detector to detect the face we need to blur. OneAPI will be incorporated to make using the code easier in every machine.
Try your hands on Some amazing SOTA Models with Intel® one API in your browser without any installation;
In this project, I am covering 3 Models from Intel Model Zoo and evaluating them powered by Intel® oneAPI platform!
Overview and demonstration of Intel® Open Image Denoise in Blender 2.9. This demo explains denoising for ray tracing and provides step by step example using the Intel® Open Image Denoise in Blender 2.9 render preview. The Intel® Open Image Denoise library, part of the Intel® oneAPI rendering toolkit
This project developed: (1) a virtual dataset designed to test automated localization algorithms on planetary surfaces, such as the Moon or Mars, where GPS is unavailable; (2) a neural network approach for absolute localization by matching orbital maps with surface perspective imagery.
This work focuses on exploring the architecture of Intel CPUs and Integrated Graphics and their heterogeneous computing potential to boost performance and energy-efficiency of epistasis detection. This will be achieved making use of OpenCL, Data Parallel C++ and OpenMP programming models.
Markov decision processes provide a formal framework for a computer to make decisions autonomously and intelligently when the effects of its actions are not deterministic. To solve this computationally complex problem, we experiment with scheduling on a low-power heterogeneous CPU+GPU SoC platform.
This project demonstrates the using of the Intel® oneAPI library to deliver a modern code in Data Parallel C++, implementing a Parallel Max-Miner algorithm to optimize the performance of the association rules learning (ARL) process