Profile Job Results
Jobs
jpre2qj95
Results Ready
Name
deeplabv3_resnet50_w8a8
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 3, 520, 520]Completion Time
10/26/2025, 1:12:14 AM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.23.0
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2025.10.21.0
Estimated Inference Time
1.22 s
Estimated Peak Memory Usage
64 ‑ 81 MB
Compute Units
CPU
95
| Stage | Time | Memory |
|---|---|---|
First App Load | 385 ms | 111‑122 MB |
Subsequent App Load | 355 ms | 109‑123 MB |
Inference | 1.22 s | 64‑81 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device