Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp2oyl9qg
Results Ready
Name
bevdet_pooler
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
sensor2keyegos: float32[1, 6, 4, 4]
inv_intrins: float32[1, 6, 3, 3]
post_trans: float32[1, 6, 1, 3]
inv_post_rots: float32[1, 6, 3, 3]
depth: float32[1, 6, 59, 16, 44]
feat: float32[1, 6, 64, 16, 44]
Completion Time
10/3/2026, 3:51:20 PM
Options
--compute_unit cpu
Versions
  • QAIRT: v2.50.0.260828221209
  • QNN Backend API: 1.1.0
  • QNN Core API: 2.39.0
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2026.09.25.0
Estimated Inference Time
195 ms
Estimated Peak Memory Usage
4 ‑ 8 MB
Compute Units
CPU
281
StageTimeMemory
First App Load
193 ms400‑401 MB
Subsequent App Load
208 ms458‑951 MB
Inference
195 ms4‑8 MB
QNNValue
context_options.htp_options.performance_modeBURST
default_graph_options.htp_options.optimizations[0].typeFINALIZE_OPTIMIZATION_FLAG
default_graph_options.htp_options.optimizations[0].value3.0
default_graph_options.htp_options.precisionFLOAT16
default_graph_options.htp_options.vtcm_size0

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

Run on device