89
edits
Changes
m
no edit summary
- "The first execution of model inference using the NN API always takes many times longer, because of model graph initialization needed by the GPU/ML module"
- Profiling? ma rallenta esecuzione...{ $ 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 ==