Profile Job Results
Jobs
jnp1m83kp
Results Ready
Name
wideresnet50_quantized
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_tensor: uint8[1, 224, 224, 3]Completion Time
8/27/2024, 8:54:08 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
1.77 ms
Estimated Peak Memory Usage
0 - 595 MB
Compute Units
NPU
82
| Stage | Time | Memory |
|---|---|---|
First App Load | 823 ms | 435-437 MB |
Subsequent App Load | 269 ms | 68-663 MB |
Inference | 1.77 ms | 0-595 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