Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
BEVDet

Profile Job Results

Jobs
jpree3e05
Results Ready
Name
bevdet_float
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 18, 256, 704]
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
10/26/2025, 5:54:26 AM
Options
--qairt_version latest --compute_unit cpu
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2025.10.21.0
Estimated Inference Time
2.05 s
Estimated Peak Memory Usage
128 ‑ 132 MB
Compute Units
CPU
492
StageTimeMemory
First App Load
263 ms528‑529 MB
Subsequent App Load
216 ms428‑430 MB
Inference
2.05 s128‑132 MB
TensorFlow LiteValue
number_of_threads4
XNNPACK DelegateValue

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

Run on device