dave_user
207
edits
Changes
no edit summary
Specifically, it illustrates the execution of an inference application (fruit classifier) that makes use of the model described in [[ML-TN-001_-_AI_at_the_edge:_comparison_of_different_embedded_platforms_-_Part_1#Reference_application_.231:_fruit_classifier|this section]] when executed on the [https://www.xilinx.com/products/boards-and-kits/zcu104.html Xilinx Zynq UltraScale+ MPSoC ZCU104 Evaluation Kit]. The results achieved are also compared to the ones produced by the platforms that were considered in the [[ML-TN-001_-_AI_at_the_edge:_comparison_of_different_embedded_platforms_-_Part_1#Articles_in_this_series|previous articles of this series]].
===Environment=Building the application==TBD.{| class="wikitable"* questo è un elenco puntato 1|+ scrivo nel blocco dell'elenco puntato!!Component!Name/version!Version|-| rowspan="* questo è un elenco puntato 2" |Host||||-||||-| rowspan="2" |Target|Hardware platform|ZCU104||-|Linux BSP|Petalinux|2020.1|} == Model deployment ==* questo è un elenco puntato 3* questo è un elenco puntato 4== Building Testing and running the application performances==In order to have reproducible and reliable results, some measures were taken:* The inference was repeated several times and the average execution time was computed* All the files required to run the test—the executable, the image files, etc.—are stored on a tmpfs RAM disk in order to make file system/storage medium overhead neglectableTBD. == Results ==