Profile Job Results
Jobs
jpv76n37p
Results Ready
Name
bevdet_pooler
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
sensor2keyegos: float32[1, 6, 4, 4]inv_intrins: float32[1, 6, 3, 3]post_trans: float32[1, 6, 1, 3]inv_post_rots: float32[1, 6, 3, 3]depth: float32[1, 6, 59, 16, 44]feat: float32[1, 6, 64, 16, 44]Completion Time
7/25/2026, 8:22:15 PM
Options
--compute_unit cpuVersions
- QAIRT: v2.45.0.260326154327
- QNN Backend API: 1.1.0
- QNN Core API: 2.34.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.07.17.0
Estimated Inference Time
175 ms
Estimated Peak Memory Usage
4 ‑ 7 MB
Compute Units
CPU
283
| Stage | Time | Memory |
|---|---|---|
First App Load | 232 ms | 461‑463 MB |
Subsequent App Load | 152 ms | 0‑496 MB |
Inference | 175 ms | 4‑7 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device