Profile Job Results
Jobs
jgn64z4m5
Results Ready
Name
face_det_lite_quantized
Target Device
- SA7255P ADP
- Android 14
- Qualcomm® SA7255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input: uint8[1, 480, 640, 1]Completion Time
1/8/2025, 7:32:28 AM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.28.0.241029232508_102474-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-2025.01.04.0
Estimated Inference Time
3.13 ms
Estimated Peak Memory Usage
0 ‑ 13 MB
Compute Units
NPU
90
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.40 s | 26‑36 MB |
Subsequent App Load | 1.45 s | 24‑46 MB |
Inference | 3.13 ms | 0‑13 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