READ ME File For 'Dataset supporting the publication "Efficient Deployment of Early-Exit DNN Architectures on FPGA Platforms"'

Dataset DOI: 10.5258/SOTON/D2885

Date that the file was created: May, 2024

-------------------
GENERAL INFORMATION
-------------------

ReadMe Author: Anastasios Dimitriou, University of Southampton 

Date of data collection: 09/2023-10/2023

Information about geographic location of data collection: UK


--------------------------
SHARING/ACCESS INFORMATION
-------------------------- 

Licenses/restrictions placed on the data, or limitations of reuse: CC BY

This dataset supports the publication:

AUTHORS: Anastasios Dimitriou, Jonathon Hare, Geoff V. Merrett
TITLE: Efficient Deployment of Early-Exit DNN Architectures on FPGA Platforms
CONFERENCE: Design, Automation & Test in Europe Conference 


Related projects: Engineering and Physical Sciences Research Council (EPSRC) under EP/S030069/1

Licence: CC BY 4.0

--------------------
DATA & FILE OVERVIEW
--------------------

This dataset contains:
 
'Fig2a.csv': Data supporting Fig. 2 (a). Execution time in ms of the Dynamic Deep Neural Network on different platforms. (CPU, CPU+GPU, Jetson Xavier and FPGA  Xilinx ZCU106) 
'Fig2b.csv': Data supporting Fig. 2 (b). Energy consumption and needed power for the execution of the Dynamic Deep Neural network on different platforms. (CPU, CPU+GPU, Jetson Xavier and FPGA  Xilinx ZCU106).
'Fig3.csv' : Data supporting Fig. 3 . Number of samples to be firstly correctly predicted after the execution of every layer on ResNet-32.