Profile Job Results
Jobs
jn5q4dvog
Results Ready
Name
deeplabv3_plus_mobilenet_quantized
Target Device
- Snapdragon X Elite CRD
- Windows 11
- Snapdragon® X Elite | SC8380XP
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 3, 513, 513]Completion Time
8/11/2024, 8:45:53 AM
Versions
- ONNX Runtime: 1.18.1
- QNN: v2.24.0.240626131148_96320
- Windows: Windows 11 (26100)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
17.4 ms
Estimated Peak Memory Usage
71 MB
Compute Units
NPU
120
CPU
51
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.28 s | 405 MB |
Subsequent App Load | 2.50 s | 25 MB |
Inference | 17.4 ms | 71 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" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device