Profile Job Results
Jobs
jp4lmdk15
Results Ready
Name
mediapipe_pose_MediaPipePoseDetector
Target Device
- SA8295P ADP
- Android 14
- Qualcomm® SA8295P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image
: float32[1, 128, 128, 3]Completion Time
11/26/2024, 12:19:22 PM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.28.0.241029232508_102474-auto
- Android: 14 (UQ1A.240205.002)
- Build ID: SA8295P.HQX.4.5.6.0-00006-STD.PROD-1
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
2.34 ms
Estimated Peak Memory Usage
0 ‑ 10 MB
Compute Units
NPU
106
Stage | Time | Memory |
---|---|---|
First App Load | 643 ms | 50‑56 MB |
Subsequent App Load | 662 ms | 46‑68 MB |
Inference | 2.34 ms | 0‑10 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