Profile Job Results
Jobs
jp4lmk9q5
Results Ready
Name
posenet_mobilenet_quantized
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image
: uint8[1, 513, 257, 3]Completion Time
11/26/2024, 11:39:46 AM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.28.2.241116104011_103376
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
2.29 ms
Estimated Peak Memory Usage
0 ‑ 21 MB
Compute Units
NPU
48
Stage | Time | Memory |
---|---|---|
First App Load | 2.65 s | 72‑80 MB |
Subsequent App Load | 2.54 s | 45‑74 MB |
Inference | 2.29 ms | 0‑21 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