Profile Job Results
Jobs
jpvqd0dmg
Results Ready
Name
deeplabv3_resnet50
Target Device
- XR2 Gen 2 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 520, 520, 3]Completion Time
3/11/2025, 7:23:33 PM
Options
--compute_unit gpuVersions
- TensorFlow Lite: 2.17.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.03.06.0
Estimated Inference Time
1.12 s
Estimated Peak Memory Usage
23 ‑ 56 MB
Compute Units
GPU
98
CPU
2
| Stage | Time | Memory |
|---|---|---|
First App Load | 58.9 s | 465‑482 MB |
Subsequent App Load | 1.58 min | 185‑227 MB |
Inference | 1.12 s | 23‑56 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