Profile Job Results
Jobs
jgz364v45
Results Ready
Name
resnet_mixed
Target Device
- SA8295P ADP
- Android 14
- Qualcomm® SA8295P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
video: float32[1, 3, 16, 112, 112]Completion Time
1/8/2025, 4:10:36 AM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.28.0.241029232508_102474-auto
- Android: 14 (UQ1A.240205.002)
- Build ID: SA8295P.HQX.4.5.6.0-00006-STD.PROD-1
- AI Hub: aihub-2025.01.04.0
Estimated Inference Time
203 ms
Estimated Peak Memory Usage
31 ‑ 59 MB
Compute Units
NPU
50
CPU
5
| Stage | Time | Memory |
|---|---|---|
First App Load | 6.82 s | 478‑484 MB |
Subsequent App Load | 6.91 s | 478‑532 MB |
Inference | 203 ms | 31‑59 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| 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