Profile Job Results
Jobs
jegnwedkg
Results Ready
Name
unet_segmentation
Target Device
- SA8775 (Proxy)
- Android 13
- Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 640, 1280, 3]Completion Time
8/27/2024, 8:32:56 AM
Versions
- TensorFlow Lite: 2.16.1
- QNN TfLite Delegate: v2.25.0.240728104910_97711
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.08.23.0
Estimated Inference Time
147 ms
Estimated Peak Memory Usage
6 - 9 MB
Compute Units
NPU
32
| Stage | Time | Memory |
|---|---|---|
First App Load | 4.68 s | 1 GB |
Subsequent App Load | 280 ms | 75-577 MB |
Inference | 147 ms | 6-9 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