Profile Job Results
Jobs
jp8q9ywkp
Results Ready
Name
face_det_lite_quantized
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input
: uint8[1, 480, 640, 1]Completion Time
1/21/2025, 3:28:13 PM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.28.2.241116104011_103376
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.01.04.0
Estimated Inference Time
276 μs
Estimated Peak Memory Usage
0 ‑ 9 MB
Compute Units
NPU
90
Stage | Time | Memory |
---|---|---|
First App Load | 333 ms | 24‑25 MB |
Subsequent App Load | 419 ms | 16‑17 MB |
Inference | 276 μs | 0‑9 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