89
edits
Changes
m
→Results
=== Version 3 ===
A new C++ application was written to apply the inference to the frames captured from an image sensor ([https://cdn.sparkfun.com/datasheets/Sensors/LightImaging/OV5640_datasheet.pdf OV5640]) instead of images retrieved from files. It uses OpenCV 4.2.0 to control the image sensor. Like version 2, inference run on NPU, so only the fully-quantized model was tested with the version 3 application. Note that with this image sensor, the frame rate is capped at 30 fps.
== Running the applications ==
==== <big>Profiling model execution on NPU</big> ====
The following block shows the eIQ profiler log. "The log captures detailed information of the execution clock cycles and DDR data transmission in each layer". Note that the time needed for inference is longer than usual while the profiler overhead is added. The input command and the messages printed from the application are in bold to separate them from the log.
'''root@imx8mpevk:/mnt/ramdisk/image_classifier_eIQ_plus# build/image_classifier_cv 3 my_fruits_model_qatlegacy.tflite labels.txt testdata/red-apple1.jpg '''
INFO: Created TensorFlow Lite delegate for NNAPI.
=== <big>Version 3</big> ===
TBD
The following image shows the execution of the third version of the classifier on the embedded platform. Note that with this image sensor, the frame rate is capped at 30 fps.
[[File:ML-TN-001 4 camera photo.jpg|thumb|center|600px]]
During the execution, <code>htop</code> was used to monitor the system. The following screenshot shows the system status while executing the application.
[[File:ML-TN-001 4 camera htop.png|thumb|center|600px]]
== Results ==
TBD
("In addition, this document compares the results achieved 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]]")