Profile Job Results
Jobs
jw560rey5
Results Ready
Name
deeplabv3_plus_mobilenet_quantized
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 513, 513, 3]Completion Time
8/27/2024, 9:10:16 AM
Versions
- TensorFlow Lite: 2.16.1
- QNN TfLite Delegate: v2.25.0.240728104910_97711
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.08.23.0
Estimated Inference Time
3.31 ms
Estimated Peak Memory Usage
0 - 5 MB
Compute Units
NPU
104
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.64 s | 82-83 MB |
Subsequent App Load | 175 ms | 7-69 MB |
Inference | 3.31 ms | 0-5 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device