Profile Job Results
Jobs
jpr2yyn05
Results Ready
Name
bisenet
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 720, 960, 3]Completion Time
7/20/2025, 2:02:47 AM
Versions
- TensorFlow Lite: 2.17.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.07.12.0
Estimated Inference Time
56.0 ms
Estimated Peak Memory Usage
47 ‑ 137 MB
Compute Units
GPU
68
| Stage | Time | Memory |
|---|---|---|
First App Load | 44.7 s | 374‑381 MB |
Subsequent App Load | 43.1 s | 251‑349 MB |
Inference | 56.0 ms | 47‑137 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