Bureaucrats, dave_user, Administrators
4,650
edits
Changes
→Introduction
'''[MHz]'''
|12001300
|-
|'''SDRAM memory frequency (LPDDR4)'''
* 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 neglectable.
The following blocks show sections detail the execution of the classifier on the embedded platform. With During the floatingexecution, the well-point modelknow [https://en.wikipedia.org/wiki/Htop <code>htop</code>] utility was used to monitor the systems. Also, the [https://www.tensorflow.org/lite/performance/best_practices#tweak_the_number_of_threads number of threads] was tweaked in order to test different configurations.
=== Floating-point model ===
<pre class="board-terminal">
root@imx8qmmek:~/devel/image_classifier_eIQ# ./image_classifier_cv 2 my_converted_model.tflite labels.txt testdata/red-apple1.jpg
</pre>
==== Tweaking the number of threads ====
TBD
<pre class="board-terminal">
root@imx8qmmek:~/devel/image_classifier_eIQ# ./image_classifier_cv 2 my_fruits_model_1.12_quant.tflite labels.txt testdata/red-apple1.jpg
</pre>
==== Tweaking the number of threads ====
TBD
<pre class="board-terminal">
root@imx8qmmek:~/devel/image_classifier_eIQ# ./image_classifier_cv 3 my_fruits_model_qatlegacy.tflite labels.txt testdata/red-apple1.jpg
1 Red Apple
</pre>
==== Tweaking the number of threads ====
TBD
== Results ==
