Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
FCN-ResNet50

Profile Job Results

Jobs
jgoen7jdp
Results Ready
Name
fcn_resnet50
Target Device
  • QCS8450 (Proxy)
  • Android 13
  • Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 520, 520, 3]
Completion Time
5/9/2026, 9:38:06 AM
Versions
  • LiteRT: 1.4.3
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2026.04.25.0
Estimated Inference Time
23.2 ms
Estimated Peak Memory Usage
0 ‑ 264 MB
Compute Units
NPU
82
StageTimeMemory
First App Load
3.09 s238‑247 MB
Subsequent App Load
229 ms33‑300 MB
Inference
23.2 ms0‑264 MB
Lite RTValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.optimization_strategykHtpOptimizeForInferenceO3
htp_options.useConvHmxtrue

Sign up to run this model on a hosted Qualcomm® device!

Run on device