Profile Job Results
Jobs
jqp4e491g
Results Ready
Name
inception_v3_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
8/11/2024, 8:34:05 AM
Versions
- TensorFlow Lite: 2.16.1
- QNN TfLite Delegate: v2.24.0.240626131148_96320
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
0.45 ms
Estimated Peak Memory Usage
0 - 67 MB
Compute Units
NPU
146
| Stage | Time | Memory |
|---|---|---|
First App Load | 418 ms | 153-160 MB |
Subsequent App Load | 138 ms | 19-89 MB |
Inference | 0.45 ms | 0-67 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