Deploying Deep Neural Networks to Embedded GPUs

How to create, train and deploy deep neural networks for embedded GPUs
385 Downloads
Updated 16 Nov 2020

View License

Designing and deploying deep learning and computer vision applications to embedded GPU platforms is challenging because of resource constraints inherent in embedded devices. This demo shows how to create and train deep neural networks for image classification, and shows how to deploy trained network using GPU Coder. These are the files for the "Deploying Deep Neural Networks to Embedded GPUs and CPUs" Japanese webinar which debuted in April 2018. The images used in this demo are from CDC DPDx Parasite Image Linrary.
https://www.cdc.gov/dpdx/index.html
本ファイルは、2018年4月に開催されたWebinar、"ディープラーニングの組み込み機器実装ソリューション~GPU/CPU編~"で使用されたものになります。血液塗抹検査画像を使い、寄生している病原虫の種類を分類するタスクをAlexNetベースの転移学習で実現し、学習したネットワークをGPU Coderを利用してMATLAB外の環境に配布する流れをご紹介します。また、本デモでは米国CDC DPDx Parasite Image Libraryにて公開されている画像データを利用しています。https://www.cdc.gov/dpdx/index.html
[Keyward]
画像処理・画像分類・ディープラーニング・DeepLearning・デモ・IPCVデモ・ニューラルネットワーク

Cite As

Kei Otsuka (2024). Deploying Deep Neural Networks to Embedded GPUs (https://www.mathworks.com/matlabcentral/fileexchange/66881-deploying-deep-neural-networks-to-embedded-gpus), MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2020b
Compatible with R2020b
Platform Compatibility
Windows macOS Linux
Categories
Find more on Get Started with GPU Coder in Help Center and MATLAB Answers

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

classifyBloodSmearImages

Version Published Release Notes
2.0.0.0

Add LiveScript

1.0.0.0

Update some m files