Profile Job Results
Jobs
jgnzxq9qg
Results Ready
Name
maskrcnn_roi_head
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.9
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
features_0: float32[1, 256, 200, 200]features_1: float32[1, 256, 100, 100]features_2: float32[1, 256, 50, 50]features_3: float32[1, 256, 25, 25]proposals_boxes: float32[1, 200, 4]Completion Time
9/19/2026, 11:49:28 PM
Options
--qairt_version latestVersions
- ONNX Runtime: 1.27.1
- QAIRT: v2.50.0.260828221209
- Qualcomm Linux: 1.9-ver.1.0
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
113 ms
Estimated Peak Memory Usage
113 ‑ 212 MB
Compute Units
NPU
160
CPU
88
| Stage | Time | Memory |
|---|---|---|
First App Load | 25.4 s | 431‑432 MB |
Subsequent App Load | 528 ms | 99‑100 MB |
Inference | 113 ms | 113‑212 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