Profile Job Results
Jobs
jpvl4v8r5
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
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
9/19/2026, 2:00:14 PM
Options
--qairt_version latest --compute_unit cpuVersions
- QAIRT: v2.50.0.260828221209
- QNN Backend API: 1.1.0
- QNN Core API: 2.39.0
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
373 ms
Estimated Peak Memory Usage
269 ‑ 736 MB
Compute Units
CPU
281
| Stage | Time | Memory |
|---|---|---|
First App Load | 47.1 ms | 0‑1 MB |
Subsequent App Load | 48.8 ms | 0‑1 MB |
Inference | 373 ms | 269‑736 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