Profile Job Results
Jobs
jygz0w4z5
Results Ready
Name
ffnet_54s
Target Device
- XR2 Gen 2 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 1024, 2048, 3]Completion Time
8/27/2024, 10:16:51 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
32.4 ms
Estimated Peak Memory Usage
2 - 87 MB
Compute Units
NPU
113
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.51 s | 341-350 MB |
Subsequent App Load | 169 ms | 36-121 MB |
Inference | 32.4 ms | 2-87 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