Profile Job Results
Jobs
j1p3rmnmp
Results Ready
Name
yolov8_det_quantized
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 640, 640, 3]Completion Time
8/27/2024, 6:43:30 AM
Versions
- TensorFlow Lite: 2.16.1
- QNN TfLite Delegate: v2.25.0.240728104910_97711
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2024.08.23.0
Estimated Inference Time
5.79 ms
Estimated Peak Memory Usage
0 - 37 MB
Compute Units
NPU
278
CPU
1
GPU
1
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.43 s | 75-83 MB |
Subsequent App Load | 388 ms | 3-42 MB |
Inference | 5.79 ms | 0-37 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 |
| GPUv2 Delegate | Value |
|---|---|
| inference_preference | TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED |
| inference_priority1 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY |
| inference_priority2 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE |
| inference_priority3 | TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION |
Sign up to run this model on a hosted Qualcomm® device!
Run on device