Profile Job Results
Jobs
jglwmkmjp
Results Ready
Name
detectron2_detection_proposal_generator
Target Device
- Dragonwing RB3 Gen 2 Vision Kit
- Qualcomm Linux 1.6
- Qualcomm® Dragonwing™ RB3 Gen 2 | QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint16[1, 3, 800, 800]Completion Time
10/3/2026, 4:48:25 PM
Options
--onnx_execution_providers qnnVersions
- ONNX Runtime: 1.30.0
- QAIRT: v2.50.0.260828221209
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
92.3 ms
Estimated Peak Memory Usage
18 ‑ 21 MB
Compute Units
NPU
94
| Stage | Time | Memory |
|---|---|---|
First App Load | 30.8 s | 470 MB |
Subsequent App Load | 483 ms | 36 MB |
Inference | 92.3 ms | 18‑21 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 | "0" |
| 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