Profile Job Results
Jobs
jp3jx413g
Results Ready
Name
yolov7_quantized
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image
: uint8[1, 640, 640, 3]Completion Time
11/26/2024, 12:58:57 PM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.28.2.241116104011_103376
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
4.51 ms
Estimated Peak Memory Usage
0 ‑ 10 MB
Compute Units
NPU
228
Stage | Time | Memory |
---|---|---|
First App Load | 2.38 s | 88‑89 MB |
Subsequent App Load | 2.41 s | 93‑232 MB |
Inference | 4.51 ms | 0‑10 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