Profile Job Results
Jobs
j5memzw7p
Results Ready
Name
deeplabv3_plus_mobilenet_quantized
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 520, 520, 3]Completion Time
3/11/2025, 9:20:20 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.0.250228225014_116386
- QNN TfLite Delegate: v2.32.0.250228225014_116386
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2025.03.06.0
Estimated Inference Time
17.2 ms
Estimated Peak Memory Usage
0 ‑ 41 MB
Compute Units
NPU
136
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.97 s | 102‑109 MB |
Subsequent App Load | 4.22 s | 108‑165 MB |
Inference | 17.2 ms | 0‑41 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