1 code implementation • 1 Dec 2021 • Priyank Kalgaonkar, Mohamed El-Sharkawy
Due to the advent of modern embedded systems and mobile devices with constrained resources, there is a great demand for incredibly efficient deep neural networks for machine learning purposes.
no code implementations • 28 Nov 2021 • Priyank Kalgaonkar, Mohamed El-Sharkawy
Intelligent edge devices with built-in processors vary widely in terms of capability and physical form to perform advanced Computer Vision (CV) tasks such as image classification and object detection, for example.
1 code implementation • 26 Jun 2021 • Priyank Kalgaonkar, Mohamed El-Sharkawy
In this paper, we demonstrate the implementation of our ultra-efficient deep convolutional neural network architecture: CondenseNeXt on NXP BlueBox, an autonomous driving development platform developed for self-driving vehicles.
no code implementations • 8 Oct 2020 • Prasham Shah, Mohamed El-Sharkawy
It is trained on CIFAR-10 [4] and has a validation accuracy of 91. 13%.
no code implementations • 30 Sep 2020 • Maneesh Ayi, Mohamed El-Sharkawy
Reduced Mobilenet V2 (RMNv2) is one of those models which is specifically designed for deploying easily in embedded and mobile devices.
no code implementations • 8 Jan 2020 • Maneesh Ayi, Mohamed El-Sharkawy
The baseline architecture of our network is Mobilenet V2.