Profile Job Results
Jobs
jgnneevjg
Results Ready
Name
maskrcnn_roi_head
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
proposals_boxes: float32[1, 200, 4]features_0: float32[1, 200, 200, 256]features_1: float32[1, 100, 100, 256]features_2: float32[1, 50, 50, 256]features_3: float32[1, 25, 25, 256]Completion Time
8/22/2026, 4:26:09 PM
Versions
- QAIRT: v2.45.0.260326154327
- QNN Backend API: 5.45.0
- QNN Core API: 2.34.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.08.14.0
Estimated Inference Time
244 ms
Estimated Peak Memory Usage
50 ‑ 52 MB
Compute Units
NPU
238
| Stage | Time | Memory |
|---|---|---|
First App Load | 21.4 s | 432‑433 MB |
Subsequent App Load | 315 ms | 0‑245 MB |
Inference | 244 ms | 50‑52 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| 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