Open main menu

DAVE Developer's Wiki β

Changes

m
no edit summary
==== <big>Profiling model execution on NPU</big> ====
The following block shows the 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.
'''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.'''
#productname=VIPNano-D+I, pid=0x9f
Created VX Thread: 0xa3ee5fb0
execution time: 187 us
'''Warmup time: 3602.98 ms'''
'''Original image size: 600x600x3'''
Cropped image size: 600x600x3
Resized image size: 224x224x3
Selected order of channels: RGB
Selected pixel values range: NA
Filling time: 0.195005 ms'''
prev_ptrs = 0xffffa369c040
execution time: 151 us
'''Inference time 3: 2.61483 ms'''
'''Average inference time: 2.52716 ms'''
Total prediction time: 2.72216 ms
Output tensor index: 5
Output tensor name: activation_5/Softmax
Top results:
1 Red Apple'''
prev_ptrs = 0xffffa369c040
Exit VX Thread: 0xa3ee5fb0
{
 
$ export CNN_PERF=1 NN_EXT_SHOW_PERF=1 VIV_VX_DEBUG_LEVEL=1 VIV_VX_PROFILE=1
 
$ build/image_classifier_cv ... > viv_test_app_profile.log 2>&1
 
}
 
=== <big>Version 3</big> ===
== Results ==
89
edits