Profile Job Results
Jobs
j5qr22mnp
Results Ready
Name
bisenet
Target Device
- SA8775P ADP
- Android 14
- Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 720, 960, 3]Completion Time
7/20/2025, 2:11:20 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-2025.07.12.0
Estimated Inference Time
135 ms
Estimated Peak Memory Usage
48 ‑ 96 MB
Compute Units
GPU
68
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.35 min | 169‑180 MB |
Subsequent App Load | 1.28 min | 159‑210 MB |
Inference | 135 ms | 48‑96 MB |
| 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device