Profile Job Results
Jobs
jep2z7q4p
Results Ready
Name
regnet_quantized
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint8[1, 224, 224, 3]Completion Time
8/27/2024, 12:52:37 PM
Versions
- TensorFlow Lite: 2.16.1
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2024.08.23.0
Estimated Inference Time
29.4 ms
Estimated Peak Memory Usage
0 - 73 MB
Compute Units
GPU
116
| Stage | Time | Memory |
|---|---|---|
First App Load | 5.30 s | 269-278 MB |
Subsequent App Load | 399 ms | 120-197 MB |
Inference | 29.4 ms | 0-73 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device