Profile Job Results

Jobs
j1glw868p
Results Ready
Name
mediapipe_selfie
Target Device
  • QCS8550 (Proxy)
  • Android 12
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 256, 256, 3]
Completion Time
8/11/2024, 7:18:58 AM
Versions
  • TensorFlow Lite: 2.16.1
  • QNN TfLite Delegate: v2.24.0.240626131148_96320
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2024.08.01.0
Estimated Inference Time
0.73 ms
Estimated Peak Memory Usage
0 - 1 MB
Compute Units
NPU
118
StageTimeMemory
First App Load
353 ms26-27 MB
Subsequent App Load
154 ms0-35 MB
Inference
0.73 ms0-1 MB
TensorFlow LiteValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.useConvHmxtrue

Sign up to run this model on a hosted Qualcomm® device!

Run on device