Profile Job Results
Jobs
jygz04nz5
Results Ready
Name
resnext101_quantized
Target Device
- Samsung Galaxy S24+
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint8[1, 224, 224, 3]Completion Time
8/27/2024, 6:51:44 PM
Versions
- TensorFlow Lite: 2.16.1
- QNN TfLite Delegate: v2.25.0.240728104910_97711
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.08.23.0
Estimated Inference Time
2.09 ms
Estimated Peak Memory Usage
0 - 259 MB
Compute Units
NPU
150
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.88 s | 762-770 MB |
Subsequent App Load | 196 ms | 129-391 MB |
Inference | 2.09 ms | 0-259 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