Difference between revisions of "Getting started with AI on NXP i.MX8M Plus/Neural Processing Unit/Use Case experiments: Smart Parking/Serial experiments"
< Getting started with AI on NXP i.MX8M Plus | Neural Processing Unit/Use Case experiments: Smart Parking
| Line 1: | Line 1: | ||
| + | <noinclude> | ||
| + | {{Getting started with AI on NXP i.MX8M Plus/Head|next=|keywords=}} | ||
| + | </noinclude> | ||
== Purpose of Serial experiments == | == Purpose of Serial experiments == | ||
| Line 10: | Line 13: | ||
* 100 warmup inference iterations. | * 100 warmup inference iterations. | ||
* 1 valid inference iteration. | * 1 valid inference iteration. | ||
| + | <noinclude> | ||
| + | {{Getting started with AI on NXP i.MX8M Plus/Foot||}} | ||
| + | </noinclude> | ||
Revision as of 19:24, 24 November 2021
 | Getting started with AI on NXP i.MX8M Plus RidgeRun documentation is currently under development. |
|
Purpose of Serial experiments
The main goal of these experiments is to measure the execution time performance, knowing that CPU, the delegates NNAPI and XNNPACK are going to be used as a comparison between them.
This experiment consists of executing each Smart Parking stage separately, firstly the License Plate Detection by TinyYOLO v3, and secondly the License Plate Recognition by Rosetta model.
Initial conditions:
- The stages are executed sequentially.
- 100 warmup inference iterations.
- 1 valid inference iteration.
