Profile Job Results
Jobs
jgz3xyv65
Results Ready
Name
face_attrib_net
Target Device
- Snapdragon 8 Elite QRD
- Android 15
- Snapdragon® 8 Elite | SM8750
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 3, 128, 128]Completion Time
11/10/2024, 9:44:51 AM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.27.1.240926142112_100894
- Android: 15 (AQ3A.240829.003)
- Build ID: Pakala.LA.1.0.r1-01032-STD.PROD-1
- AI Hub: aihub-2024.10.28.0
Estimated Inference Time
658 μs
Estimated Peak Memory Usage
0 ‑ 60 MB
Compute Units
NPU
161
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.25 s | 285‑293 MB |
Subsequent App Load | 82.2 ms | 34‑95 MB |
Inference | 658 μs | 0‑60 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