Profile Job Results
Jobs
jp8q6z3op
Results Ready
Name
ffnet_54s_quantized
Target Device
- XR2 Gen 2 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 1024, 2048, 3]Completion Time
11/26/2024, 1:24:07 PM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.28.2.241116104011_103376
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
5.90 ms
Estimated Peak Memory Usage
1 ‑ 32 MB
Compute Units
NPU
120
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.41 s | 172‑180 MB |
Subsequent App Load | 1.51 s | 142‑217 MB |
Inference | 5.90 ms | 1‑32 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