Profile Job Results
Jobs
jpx9xj41p
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
3/11/2025, 1:18:56 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.0.250228225014_116386
- QNN TfLite Delegate: v2.32.0.250228225014_116386
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.03.06.0
Estimated Inference Time
167 ms
Estimated Peak Memory Usage
6 ‑ 463 MB
Compute Units
NPU
32
| Stage | Time | Memory |
|---|---|---|
First App Load | 5.63 s | 481‑482 MB |
Subsequent App Load | 5.31 s | 528‑531 MB |
Inference | 167 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