Profile Job Results
Jobs
jep2ozeqg
Results Ready
Name
deeplabv3_plus_mobilenet_quantized
Target Device
- SA8255 (Proxy)
- Android 13
- Qualcomm® SA8255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image
: uint8[1, 513, 513, 3]Completion Time
8/11/2024, 8:43:52 AM
Versions
- QNN: v2.24.0.240626131148_96320
- QNN Backend API: 5.24.0
- QNN Core API: 2.17.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
4.05 ms
Estimated Peak Memory Usage
1 - 2 MB
Compute Units
NPU
99
Stage | Time | Memory |
---|---|---|
First App Load | 189 ms | 1-2 MB |
Subsequent App Load | 171 ms | 1-2 MB |
Inference | 4.05 ms | 1-2 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