Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jg9lv1wlg
Results Ready
Name
posenet_mobilenet_quantized
Target Device
  • XR2 Gen 2 (Proxy)
  • Android 13
  • Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 513, 257, 3]
Completion Time
1/21/2025, 1:08:59 PM
Versions
  • TensorFlow Lite: 2.17.0
  • QNN TfLite Delegate: v2.28.2.241116104011_103376
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2025.01.04.0
Estimated Inference Time
755 μs
Estimated Peak Memory Usage
0 ‑ 30 MB
Compute Units
NPU
48
StageTimeMemory
First App Load
554 ms74‑83 MB
Subsequent App Load
825 ms66‑125 MB
Inference
755 μs0‑30 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