Profile Job Results
Jobs
jgj2772x5
Results Ready
Name
bisenet
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 720, 960, 3]Completion Time
8/24/2025, 7:22:08 AM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.37.0.250724175447_124859
- QNN TfLite Delegate: v2.37.0.250724175447_124859
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.08.21.0
Estimated Inference Time
46.0 ms
Estimated Peak Memory Usage
20 ‑ 39 MB
Compute Units
NPU
65
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.97 s | 242‑243 MB |
Subsequent App Load | 1.71 s | 287‑290 MB |
Inference | 46.0 ms | 20‑39 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