Lukas SteindlOptimizing deep neural networks for efficient dronebased ragweed detectionMasterTU Wien
Nikolas AlgePower Profiling of Machine Learning Accelerators using MLPerfBachelorTU Wien


Andreas GlinsererAutopruning mit Intel Distiller und Evaluation auf einem Jetson Xavier AGXMasterTU Wien
Bernhard HaasCompressing MobileNet With Shunt Connections for NVIDIA HardwareMasterTU Wien
Michael OpitzEfficient Ensembles for Deep LearningPh.DTU Graz
Matvey IvanovEmbedded Machine Learning DemonstratorBachelorTU Wien
Dominik DallingerFPGA optimized dynamic post-training quantization of TinyYoloV3BachelorTU Wien
Amid MozelliA Study on Confidence: an Unsupervised Multi-Agent Machine Learning ExperimentBachelorTU Wien
Lukas BaischerFPGA Based Embedded Neural Network Object DetectorMasterTU Wien


Kaleab Alemayehu KinfuLifelong Learning for Autonomous Vehicles: Monocular Depth EstimationMasterTU Graz
Anam ZahraAutonomous Vehicle Self-localization in Noisy EnvironmentsMasterTU Graz
Marco WuschnigAuswertung verschiedener Methoden der Hyperparameteroptimierung in Machine LearningBachelorTU Wien
Julian RothAuswertung von Cloudbasierten Machine Learning Frameworks für Supervised Machine LearningBachelorTU Wien
Rudolf WörndleContinual Domain-Incremental Learning for Object DetectionMasterTU Graz


Blackthorn Latency Estimation Toolkit for Neural Networks (Nvidia)
Embedded Machine Learning Scripts and Guides We collect scripts and guides that help us in our everyday work to setup software and frameworks. This repository is also the source of an EML Toolbox that aims to easyily implement machine learning toolchains.
ANNETTE Accurate Neural Network Execution Time Estimation
Re-Implementation of SqueezeNas SqueezeNAS Repository with reimplementation for a custom semenatic segementation task
EML Mobile Phone Photo Detection Application A mobile phone application for applying detection networks on captured fotos and camera streams
Shunt Connector Neural network compression technique called 'Shunt connection' using Keras and TensorFlow 2.x as its backend.
MobileNetV3-Segmentation-Keras Semantic segmentation version of the MobileNetV3 architecture (source), which is inspired by the DeeplabV3 architecture. The model is implemented using Keras and TensorFlow 2.x.


See the Publication section.