Profile Job Results
Jobs
jlpenr70p
Results Ready
Name
resnet18_quantized
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint8[1, 224, 224, 3]Completion Time
8/27/2024, 8:10:20 AM
Versions
- QNN: v2.25.0.240728104910_97711
- QNN Backend API: 5.25.0
- QNN Core API: 2.18.0
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2024.08.23.0
Estimated Inference Time
2.10 ms
Estimated Peak Memory Usage
0 - 8 MB
Compute Units
NPU
37
| Stage | Time | Memory |
|---|---|---|
First App Load | 241 ms | 1-9 MB |
Subsequent App Load | 255 ms | 1-8 MB |
Inference | 2.10 ms | 0-8 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.precision | FLOAT16 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device