Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jpv6ev6k5
Results Ready
Name
foot_track_net_quantized
Target Device
  • SA8255 (Proxy)
  • Android 13
  • Qualcomm® SA8255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 480, 640, 3]
Completion Time
11/26/2024, 12:56:40 PM
Versions
  • TensorFlow Lite: 2.17.0
  • QNN TfLite Delegate: v2.28.2.241116104011_103376
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2024.11.22.0
Estimated Inference Time
1.15 ms
Estimated Peak Memory Usage
0 ‑ 9 MB
Compute Units
NPU
146
StageTimeMemory
First App Load
538 ms51‑52 MB
Subsequent App Load
491 ms21‑97 MB
Inference
1.15 ms0‑9 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