Profile Job Results
Jobs
jgok2mv4p
Results Ready
Name
unet_segmentation
Target Device
- SA8775P ADP
- Android 14
- Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 640, 1280, 3]Completion Time
4/8/2025, 1:01:40 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.0.250228225014_116386-auto
- QNN TfLite Delegate: v2.32.0.250228225014_116386-auto
- Android: 14 (UQ1A.240205.002)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00011-STD.PROD-1.89321.2
- AI Hub: aihub-2025.03.24.0
Estimated Inference Time
5.22 min
Estimated Peak Memory Usage
6 ‑ 91 MB
Compute Units
NPU
32
| Stage | Time | Memory |
|---|---|---|
First App Load | 426 min | 529‑539 MB |
Subsequent App Load | 421 min | 520‑618 MB |
Inference | 5.22 min | 6‑91 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device