Profile Job Results
Jobs
jprxzjq0p
Results Ready
Name
detectron2_panoptic_seg_proposal_generator
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 3, 800, 800]Completion Time
10/20/2026, 8:02:33 AM
Options
--qairt_version 2.50Versions
- ONNX Runtime: 1.30.0
- QNN Execution Provider: 2.5.0
- QAIRT: v2.50.0.260828221209
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.10.10.0
Estimated Inference Time
84.3 ms
Estimated Peak Memory Usage
222 ‑ 226 MB
Compute Units
NPU
340
CPU
15
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.83 min | 1 GB |
Subsequent App Load | 613 ms | 0‑581 MB |
Inference | 84.3 ms | 222‑226 MB |
| ONNX Runtime | Value |
|---|---|
| execution_mode | SEQUENTIAL |
| intra_op_num_threads | 0 |
| inter_op_num_threads | 0 |
| enable_memory_pattern | false |
| enable_cpu_memory_arena | false |
| graph_optimization_level | ENABLE_ALL |
| QNN Execution Provider | Value |
|---|---|
| htp_performance_mode | "burst" |
| htp_graph_finalization_optimization_mode | "3" |
| enable_htp_fp16_precision | "1" |
| capture_network_visualizations | false |
| context_priority | "normal" |
| offload_graph_io_quantization | "1" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device