Profile Job Results
Jobs
j5wx3dnmp
Results Ready
Name
detectron2_detection_roi_head
Target Device
- QCS8450 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
features: uint8[1, 50, 50, 1024]proposals_boxes: uint8[1, 200, 4]Completion Time
5/30/2026, 10:08:34 PM
Versions
- LiteRT: 1.4.3
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.05.27.0
Estimated Inference Time
873 ms
Estimated Peak Memory Usage
1 ‑ 806 MB
Compute Units
NPU
178
| Stage | Time | Memory |
|---|---|---|
First App Load | 39.0 s | 941‑950 MB |
Subsequent App Load | 414 ms | 25‑832 MB |
Inference | 873 ms | 1‑806 MB |
| Lite RT | 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.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device