Profile Job Results
Jobs
jpxk36895
Results Ready
Name
hrnet_pose_quantized
Target Device
- Samsung Galaxy S23 (Family)
- Android 13
- Snapdragon® 8 Gen 2 | SM8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 256, 192, 3]Completion Time
11/26/2024, 12:39:06 PM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.28.2.241116104011_103376
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
970 μs
Estimated Peak Memory Usage
0 ‑ 21 MB
Compute Units
NPU
518
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.03 s | 171‑172 MB |
Subsequent App Load | 1.09 s | 122‑202 MB |
Inference | 970 μs | 0‑21 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