Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp2k4x4xp
Results Ready
Name
swin_tiny
Target Device
  • SA8255 (Proxy)
  • Android 13
  • Qualcomm® SA8255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: float32[1, 224, 224, 3]
Completion Time
11/26/2024, 10:22:16 AM
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
11.9 ms
Estimated Peak Memory Usage
0 ‑ 24 MB
Compute Units
NPU
837
StageTimeMemory
First App Load
21.6 s714‑715 MB
Subsequent App Load
20.8 s244‑891 MB
Inference
11.9 ms0‑24 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