Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
RegNet

Profile Job Results

Jobs
j5w2ym235
Results Ready
Name
regnet
Target Device
  • QCS6490 (Proxy)
  • Android 12
  • Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint8[1, 224, 224, 3]
Completion Time
5/20/2025, 5:15:39 PM
Versions
  • TensorFlow Lite: 2.17.0
  • QAIRT: v2.32.6.250402152434_116405
  • QNN TfLite Delegate: v2.32.6.250402152434_116405
  • Android: 12 (SP1A.210812.016)
  • AI Hub: aihub-2025.05.14.0
Estimated Inference Time
2.51 ms
Estimated Peak Memory Usage
0 ‑ 55 MB
Compute Units
NPU
116
StageTimeMemory
First App Load
2.52 s135‑141 MB
Subsequent App Load
2.60 s159‑242 MB
Inference
2.51 ms0‑55 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