Profile Job Results
Jobs
j5q6z247p
Results Ready
Name
deeplabv3_resnet50
Target Device
- SA8295P ADP
- Android 14
- Qualcomm® SA8295P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 520, 520, 3]Completion Time
11/26/2024, 3:27:03 PM
Options
--compute_unit gpuVersions
- TensorFlow Lite: 2.17.0
- Android: 14 (UQ1A.240205.002)
- Build ID: SA8295P.HQX.4.5.6.0-00006-STD.PROD-1
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
281 ms
Estimated Peak Memory Usage
6 ‑ 26 MB
Compute Units
GPU
98
CPU
2
| Stage | Time | Memory |
|---|---|---|
First App Load | 43.7 s | 384‑391 MB |
Subsequent App Load | 690 ms | 286‑309 MB |
Inference | 281 ms | 6‑26 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