Profile Job Results
Jobs
j5qrovknp
Results Ready
Name
deeplab_xception_w8a8
Target Device
- SA7255P ADP
- Android 14
- Qualcomm® SA7255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 480, 520, 3]Completion Time
10/5/2025, 2:42:26 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.38.0.250901140452_125126-auto
- QNN TfLite Delegate: v2.38.0.250901140452_125126-auto
- Android: 14 (UQ1A.240205.002)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00012-STD.PROD-5
- AI Hub: aihub-2025.09.26.0
Estimated Inference Time
20.4 ms
Estimated Peak Memory Usage
0 ‑ 113 MB
Compute Units
NPU
208
| Stage | Time | Memory |
|---|---|---|
First App Load | 21.3 s | 367‑376 MB |
Subsequent App Load | 22.0 s | 354‑564 MB |
Inference | 20.4 ms | 0‑113 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device