Profile Job Results
Jobs
jz57onrrg
Results Ready
Name
mobilenet_v2
Target Device
- SA8650 (Proxy)
- Android 13
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor
: float32[1, 224, 224, 3]Completion Time
8/11/2024, 7:14:42 AM
Versions
- TensorFlow Lite: 2.16.1
- QNN TfLite Delegate: v2.24.0.240626131148_96320
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
0.92 ms
Estimated Peak Memory Usage
0 - 1 MB
Compute Units
NPU
72
Stage | Time | Memory |
---|---|---|
First App Load | 579 ms | 112-113 MB |
Subsequent App Load | 175 ms | 1-50 MB |
Inference | 0.92 ms | 0-1 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