Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp1ozed75
Results Ready
Name
bevdet_pooler
Target Device
  • Arduino VENTUNO Q
  • Ubuntu 24.04
  • Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
depth: float32[1, 6, 59, 16, 44]
feat: float32[1, 6, 64, 16, 44]
sensor2keyegos: float32[1, 6, 4, 4]
inv_intrins: float32[1, 6, 3, 3]
inv_post_rots: float32[1, 6, 3, 3]
post_trans: float32[1, 6, 1, 3]
Completion Time
10/3/2026, 3:59:00 PM
Options
--compute_unit cpu
Versions
  • ONNX Runtime: 1.30.0
  • Qualcomm Linux: 24.04
  • AI Hub: aihub-2026.09.25.0
Estimated Inference Time
65.7 ms
Estimated Peak Memory Usage
274 ‑ 278 MB
Compute Units
CPU
279
StageTimeMemory
First App Load
72.7 ms10‑11 MB
Subsequent App Load
62.5 ms10‑11 MB
Inference
65.7 ms274‑278 MB
ONNX RuntimeValue
execution_modeSEQUENTIAL
intra_op_num_threads0
inter_op_num_threads0
enable_memory_patternfalse
enable_cpu_memory_arenafalse
graph_optimization_levelENABLE_ALL

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

Run on device