Profile Job Results
Jobs
jgjvolleg
Results Ready
Name
efficientnet_b4
Target Device
- Samsung Galaxy S24 (Family)
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor
: float32[1, 224, 224, 3]Completion Time
11/26/2024, 2:50:03 PM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.28.2.241116104011_103376
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
2.64 ms
Estimated Peak Memory Usage
0 ‑ 26 MB
Compute Units
NPU
482
Stage | Time | Memory |
---|---|---|
First App Load | 1.83 s | 659‑666 MB |
Subsequent App Load | 1.85 s | 574‑735 MB |
Inference | 2.64 ms | 0‑26 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