Profile Job Results
Jobs
jgjd72nvg
Results Ready
Name
bgnet
Target Device
- XR2 Gen 2 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 3, 416, 416]Completion Time
3/11/2025, 7:38:57 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.0.250228225014_116386
- QNN TfLite Delegate: v2.32.0.250228225014_116386
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.03.06.0
Estimated Inference Time
33.9 ms
Estimated Peak Memory Usage
1 ‑ 215 MB
Compute Units
NPU
361
| Stage | Time | Memory |
|---|---|---|
First App Load | 18.0 s | 1 GB |
Subsequent App Load | 13.0 s | 1 GB |
Inference | 33.9 ms | 1‑215 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