Profile Job Results
Jobs
jegn1nwvp
Results Ready
Name
yolov7
Target Device
- Samsung Galaxy S23 Ultra
- Android 13
- Snapdragon® 8 Gen 2 | SM8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 640, 640, 3]Completion Time
8/11/2024, 5:27:47 AM
Versions
- TensorFlow Lite: 2.16.1
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
24.7 ms
Estimated Peak Memory Usage
38 - 69 MB
Compute Units
GPU
145
CPU
70
| Stage | Time | Memory |
|---|---|---|
First App Load | 5.26 s | 185-186 MB |
Subsequent App Load | 155 ms | 39-56 MB |
Inference | 24.7 ms | 38-69 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| 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 |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device