Profile Job Results
Jobs
j5qezvk75
Results Ready
Name
unet_segmentation
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 640, 1280, 3]Completion Time
5/6/2025, 9:01:52 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.6.250402152434_116405
- QNN TfLite Delegate: v2.32.6.250402152434_116405
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.05.02.0
Estimated Inference Time
162 ms
Estimated Peak Memory Usage
6 ‑ 463 MB
Compute Units
NPU
32
| Stage | Time | Memory |
|---|---|---|
First App Load | 5.48 s | 525‑526 MB |
Subsequent App Load | 5.50 s | 533‑536 MB |
Inference | 162 ms | 6‑463 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device