Profile Job Results
Jobs
jp8q6wzkp
Results Ready
Name
quicksrnetlarge_quantized
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 128, 128, 3]Completion Time
11/26/2024, 4:28:20 PM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.28.2.241116104011_103376
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
1.44 ms
Estimated Peak Memory Usage
0 ‑ 4 MB
Compute Units
NPU
30
CPU
3
| Stage | Time | Memory |
|---|---|---|
First App Load | 313 ms | 27‑28 MB |
Subsequent App Load | 299 ms | 10‑50 MB |
Inference | 1.44 ms | 0‑4 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