Profile Job Results
Jobs
jgk86erng
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
8/8/2026, 5:05:15 PM
Options
--compute_unit cpuVersions
- ONNX Runtime: 1.27.1
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.07.31.1
Estimated Inference Time
71.2 ms
Estimated Peak Memory Usage
324 ‑ 328 MB
Compute Units
CPU
287
| Stage | Time | Memory |
|---|---|---|
First App Load | 86.8 ms | 9‑10 MB |
Subsequent App Load | 64.3 ms | 9‑10 MB |
Inference | 71.2 ms | 324‑328 MB |
| ONNX Runtime | Value |
|---|---|
| execution_mode | SEQUENTIAL |
| intra_op_num_threads | 0 |
| inter_op_num_threads | 0 |
| enable_memory_pattern | false |
| enable_cpu_memory_arena | false |
| graph_optimization_level | ENABLE_ALL |
Sign up to run this model on a hosted Qualcomm® device!
Run on device