Profile Job Results
Jobs
jgo4nkjk5
Results Ready
Name
detectron2_detection_proposal_generator
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 800, 800, 3]Completion Time
7/5/2026, 12:00:00 AM
Versions
- LiteRT: 1.4.4
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.06.19.2
Estimated Inference Time
42.7 ms
Estimated Peak Memory Usage
3 ‑ 6 MB
Compute Units
NPU
103
| Stage | Time | Memory |
|---|---|---|
First App Load | 22.1 s | 350‑351 MB |
Subsequent App Load | 267 ms | 22‑195 MB |
Inference | 42.7 ms | 3‑6 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