Profile Job Results
Jobs
jp4n1n3lg
Results Ready
Name
face_det_lite_quantized
Target Device
- SA8255 (Proxy)
- Android 13
- Qualcomm® SA8255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input: uint8[1, 480, 640, 1]Completion Time
3/11/2025, 5:43:15 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-2025.03.06.0
Estimated Inference Time
279 μs
Estimated Peak Memory Usage
0 ‑ 10 MB
Compute Units
NPU
90
| Stage | Time | Memory |
|---|---|---|
First App Load | 377 ms | 37‑38 MB |
Subsequent App Load | 329 ms | 96‑99 MB |
Inference | 279 μs | 0‑10 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