Profile Job Results
Jobs
jp4dl47vp
Results Ready
Name
simple_bev_cam
Target Device
- SA8775P ADP
- Android 14
- Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
rgb_camXs: float32[1, 6, 3, 448, 800]pix_T_cams: float32[1, 6, 4, 4]cam0_T_camXs: float32[1, 4, 4, 6]Completion Time
6/28/2025, 11:14:39 AM
Versions
- TensorFlow Lite: 2.17.0
- Android: 14 (UQ1A.240205.002)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00011-STD.PROD-1.89321.2
- AI Hub: aihub-2025.06.12.0
Estimated Inference Time
3.50 s
Estimated Peak Memory Usage
1 ‑ 2 GB
Compute Units
CPU
226
GPU
197
| Stage | Time | Memory |
|---|---|---|
First App Load | 10.9 min | 787‑797 MB |
Subsequent App Load | 10.3 min | 1 GB |
Inference | 3.50 s | 1‑2 GB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| GPUv2 Delegate | Value |
|---|---|
| inference_preference | TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED |
| inference_priority1 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY |
| inference_priority2 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE |
| inference_priority3 | TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device