Profile Job Results
Jobs
joprxx97p
Results Ready
Name
quicksrnetsmall_quantized
Target Device
- QCS8250 (Proxy)
- Android 12
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 128, 128, 3]Completion Time
8/11/2024, 6:35:25 AM
Versions
- TensorFlow Lite: 2.16.1
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
11.6 ms
Estimated Peak Memory Usage
3 - 10 MB
Compute Units
NPU
10
CPU
3
| Stage | Time | Memory |
|---|---|---|
First App Load | 259 ms | 2-3 MB |
Subsequent App Load | 25.7 ms | 1-2 MB |
Inference | 11.6 ms | 3-10 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| NNAPI Delegate | Value |
|---|---|
| accelerator_name | "qti-dsp" |
| execution_preference | kSustainedSpeed |
| allow_fp16 | true |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device