Profile Job Results
Jobs
jp3jxm8ng
Results Ready
Name
detr_resnet50_dc5
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 480, 480, 3]Completion Time
11/26/2024, 2:58:32 PM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.28.2.241116104011_103376
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
86.8 ms
Estimated Peak Memory Usage
0 ‑ 54 MB
Compute Units
NPU
789
| Stage | Time | Memory |
|---|---|---|
First App Load | 10.2 s | 953‑954 MB |
Subsequent App Load | 9.96 s | 1 GB |
Inference | 86.8 ms | 0‑54 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