Profile Job Results
Jobs
jp18z727g
Results Ready
Name
bevdet_float
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
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
1/11/2026, 7:52:15 AM
Options
--qairt_version latest --compute_unit cpuVersions
- TensorFlow Lite: 2.17.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.01.05.0
Estimated Inference Time
2.17 s
Estimated Peak Memory Usage
126 ‑ 130 MB
Compute Units
CPU
492
| Stage | Time | Memory |
|---|---|---|
First App Load | 282 ms | 529‑531 MB |
Subsequent App Load | 209 ms | 409‑591 MB |
Inference | 2.17 s | 126‑130 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device