Profile Job Results
Jobs
jlpen4q1p
Results Ready
Name
mediapipe_hand_MediaPipeHandDetector
Target Device
- Samsung Galaxy S23 Ultra
- Android 13
- Snapdragon® 8 Gen 2 | SM8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 256, 256, 3]Completion Time
8/27/2024, 11:26:00 AM
Versions
- QNN: v2.25.0.240728104910_97711
- QNN Backend API: 5.25.0
- QNN Core API: 2.18.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.08.23.0
Estimated Inference Time
0.79 ms
Estimated Peak Memory Usage
0 - 20 MB
Compute Units
NPU
195
| Stage | Time | Memory |
|---|---|---|
First App Load | 663 ms | 69-70 MB |
Subsequent App Load | 635 ms | 41-149 MB |
Inference | 0.79 ms | 0-20 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.precision | FLOAT16 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device