Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp2k8nvqp
Results Ready
Name
hrnet_pose_quantized
Target Device
  • SA8650 (Proxy)
  • Android 13
  • Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 256, 192, 3]
Completion Time
1/21/2025, 2:36:30 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
965 μs
Estimated Peak Memory Usage
0 ‑ 23 MB
Compute Units
NPU
518
StageTimeMemory
First App Load
886 ms192‑193 MB
Subsequent App Load
870 ms165‑167 MB
Inference
965 μs0‑23 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