Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
BEVDet

Profile Job Results

Jobs
jp0e41895
Results Ready
Name
bevdet
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint16[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: uint16[1, 6, 1, 3]
Completion Time
5/3/2026, 4:01:03 AM
Options
--qairt_version 2.42 --compute_unit cpu
Versions
  • ONNX Runtime: 1.24.3
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2026.04.25.0
Estimated Inference Time
2.66 s
Estimated Peak Memory Usage
398 ‑ 405 MB
Compute Units
CPU
972
StageTimeMemory
First App Load
315 ms79‑80 MB
Subsequent App Load
261 ms25‑80 MB
Inference
2.66 s398‑405 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