Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jgjr1e08p
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
9/19/2026, 1:35:11 PM
Options
--qairt_version latest --compute_unit cpu
Versions
  • Lite RT: 1.4.2
  • Qualcomm Linux: 24.04
  • AI Hub: aihub-2026.09.11.0
Estimated Inference Time
130 ms
Estimated Peak Memory Usage
127 ‑ 321 MB
Compute Units
CPU
303
StageTimeMemory
First App Load
55.9 ms65‑66 MB
Subsequent App Load
61.1 ms66 MB
Inference
130 ms127‑321 MB
Lite RTValue
number_of_threads4
XNNPACK DelegateValue

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

Run on device