Profile Job Results
Jobs
jw56omry5
Results Ready
Name
litehrnet
Target Device
- Samsung Galaxy S24+
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 3, 256, 192]Completion Time
8/11/2024, 8:15:32 AM
Versions
- TensorFlow Lite: 2.16.1
- QNN TfLite Delegate: v2.24.0.240626131148_96320
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
7.61 ms
Estimated Peak Memory Usage
6 - 87 MB
Compute Units
NPU
1225
CPU
10
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.14 s | 115-123 MB |
Subsequent App Load | 184 ms | 7-88 MB |
Inference | 7.61 ms | 6-87 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 |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device