Profile Job Results
Jobs
jpyjdd78p
Results Ready
Name
bisenet
Target Device
- SA7255P ADP
- Android 14
- Qualcomm® SA7255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 720, 960, 3]Completion Time
7/20/2025, 2:22:44 AM
Versions
- TensorFlow Lite: 2.17.0
- Android: 14 (UQ1A.240205.002)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00012-STD.PROD-5
- AI Hub: aihub-2025.07.12.0
Estimated Inference Time
328 ms
Estimated Peak Memory Usage
48 ‑ 92 MB
Compute Units
GPU
68
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.12 min | 154‑163 MB |
Subsequent App Load | 3.04 min | 148‑199 MB |
Inference | 328 ms | 48‑92 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