Profile Job Results
Jobs
joprx00kp
Results Ready
Name
yolov8_seg
Target Device
- QCS8550 (Proxy)
- Android 12
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 640, 640, 3]Completion Time
8/11/2024, 5:23:49 AM
Versions
- TensorFlow Lite: 2.16.1
- QNN TfLite Delegate: v2.24.0.240626131148_96320
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
6.48 ms
Estimated Peak Memory Usage
4 - 25 MB
Compute Units
NPU
338
| Stage | Time | Memory |
|---|---|---|
First App Load | 4.00 s | 113-115 MB |
Subsequent App Load | 191 ms | 0-70 MB |
Inference | 6.48 ms | 4-25 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