Profile Job Results
Jobs
jgk7e6k2p
Results Ready
Name
bisenet
Target Device
- Samsung Galaxy S23
- Android 13
- Snapdragon® 8 Gen 2 | SM8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 720, 960, 3]Completion Time
4/8/2025, 7:13:41 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.0.250228225014_116386
- QNN TfLite Delegate: v2.32.0.250228225014_116386
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.03.24.0
Estimated Inference Time
27.8 ms
Estimated Peak Memory Usage
9 ‑ 45 MB
Compute Units
NPU
63
| Stage | Time | Memory |
|---|---|---|
First App Load | 25.1 min | 203‑204 MB |
Subsequent App Load | 25.0 min | 224‑226 MB |
Inference | 27.8 s | 9‑45 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