Profile Job Results

Jobs
j1pv2mrjg
Results Ready
Name
mediapipe_pose_MediaPipePoseDetector
Target Device
  • SA8650 (Proxy)
  • Android 13
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 128, 128, 3]
Completion Time
8/11/2024, 7:24:27 AM
Versions
  • TensorFlow Lite: 2.16.1
  • QNN TfLite Delegate: v2.24.0.240626131148_96320
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2024.08.01.0
Estimated Inference Time
0.81 ms
Estimated Peak Memory Usage
0 - 6 MB
Compute Units
NPU
106
StageTimeMemory
First App Load
489 ms59-60 MB
Subsequent App Load
152 ms1-70 MB
Inference
0.81 ms0-6 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