Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
TrOCR

Profile Job Results

Jobs
jp1472qnp
Results Ready
Name
trocr_TrOCREncoder
Target Device
  • SA7255P ADP
  • Android 14
  • Qualcomm® SA7255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
pixel_values: float32[1, 384, 384, 3]
Completion Time
11/26/2024, 10:22:09 AM
Versions
  • QNN: v2.28.0.241029232508_102474-auto
  • QNN Backend API: 5.28.0
  • QNN Core API: 2.21.0
  • Android: 14 (UQ1A.240205.002)
  • Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00011-STD.PROD-1.89321.2
  • AI Hub: aihub-2024.11.22.0
Estimated Inference Time
249 ms
Estimated Peak Memory Usage
2 ‑ 9 MB
Compute Units
NPU
443
StageTimeMemory
First App Load
729 ms8‑14 MB
Subsequent App Load
1.34 s4‑10 MB
Inference
249 ms2‑9 MB
QNNValue
default_graph_options.htp_options.precisionFLOAT16

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

Run on device