Profile Job Results

Jobs
jvgd6d7zp
Results Ready
Name
trocr_TrOCREncoder
Target Device
  • SA8255 (Proxy)
  • Android 13
  • Qualcomm® SA8255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
pixel_values: float32[1, 384, 384, 3]
Completion Time
8/11/2024, 6:07:32 AM
Versions
  • QNN: v2.24.0.240626131148_96320
  • QNN Backend API: 5.24.0
  • QNN Core API: 2.17.0
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2024.08.01.0
Estimated Inference Time
101 ms
Estimated Peak Memory Usage
2 - 8 MB
Compute Units
NPU
443
StageTimeMemory
First App Load
249 ms2-3 MB
Subsequent App Load
215 ms1-3 MB
Inference
101 ms2-8 MB
QNNValue
context_options.htp_options.performance_modeBURST
default_graph_options.htp_options.precisionFLOAT16

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

Run on device