Profile Job Results
Jobs
jgl2rl1ep
Results Ready
Name
detr_resnet101_float
Target Device
- SA7255P ADP
- Android 14
- Qualcomm® SA7255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 640, 640, 3]Completion Time
10/5/2025, 5:02:57 PM
Versions
- QAIRT: v2.38.0.250901140452_125126-auto
- QNN Backend API: 5.38.0
- QNN Core API: 2.28.1
- Android: 14 (UQ1A.240205.002)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00012-STD.PROD-5
- AI Hub: aihub-2025.09.26.0
Estimated Inference Time
133 ms
Estimated Peak Memory Usage
4 ‑ 146 MB
Compute Units
NPU
913
| Stage | Time | Memory |
|---|---|---|
First App Load | 59.8 s | 642‑651 MB |
Subsequent App Load | 1.04 min | 661‑923 MB |
Inference | 133 ms | 4‑146 MB |
| QNN | Value |
|---|---|
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device