Profile Job Results
Jobs
j5qr6jrnp
Results Ready
Name
mediapipe_face_FaceLandmarkDetector
Target Device
- SA8295P ADP
- Android 14
- Qualcomm® SA8295P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 192, 192, 3]Completion Time
6/28/2025, 2:01:40 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.34.2.250528164111_119506-auto
- QNN TfLite Delegate: v2.34.2.250528164111_119506-auto
- Android: 14 (UQ1A.240205.002)
- Build ID: SA8295P.HQX.4.5.6.0-00006-STD.PROD-1
- AI Hub: aihub-2025.06.12.0
Estimated Inference Time
461 μs
Estimated Peak Memory Usage
0 ‑ 16 MB
Compute Units
NPU
108
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.11 s | 18‑24 MB |
Subsequent App Load | 1.11 s | 19‑45 MB |
Inference | 461 μs | 0‑16 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