Profile Job Results
Jobs
jp2k40nrp
Results Ready
Name
midas_quantized
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image
: uint8[1, 256, 256, 3]Completion Time
11/26/2024, 12:10:53 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
1.10 ms
Estimated Peak Memory Usage
0 ‑ 50 MB
Compute Units
NPU
145
Stage | Time | Memory |
---|---|---|
First App Load | 675 ms | 185‑186 MB |
Subsequent App Load | 675 ms | 205‑431 MB |
Inference | 1.10 ms | 0‑50 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