Profile Job Results
Jobs
jp3vjo1ng
Results Ready
Name
deeplabv3_resnet50
Target Device
- Samsung Galaxy S23
- Android 13
- Snapdragon® 8 Gen 2 | SM8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 520, 520, 3]Completion Time
4/8/2025, 6:41:48 PM
Options
--compute_unit gpuVersions
- TensorFlow Lite: 2.17.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.03.24.0
Estimated Inference Time
295 ms
Estimated Peak Memory Usage
0 ‑ 159 MB
Compute Units
GPU
98
CPU
2
| Stage | Time | Memory |
|---|---|---|
First App Load | 36.5 s | 494‑495 MB |
Subsequent App Load | 38.9 s | 460‑463 MB |
Inference | 295 ms | 0‑159 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