Profile Job Results
Jobs
jpy1qd8rp
Results Ready
Name
deeplabv3_resnet50
Target Device
- Snapdragon 8 Elite QRD
- Android 15
- Snapdragon® 8 Elite | SM8750
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 520, 520, 3]Completion Time
11/26/2024, 3:23:05 PM
Options
--compute_unit gpuVersions
- TensorFlow Lite: 2.17.0
- Android: 15 (AQ3A.240829.003)
- Build ID: Pakala.LA.1.0.r1-01032-STD.PROD-1
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
216 ms
Estimated Peak Memory Usage
12 ‑ 28 MB
Compute Units
GPU
98
CPU
2
| Stage | Time | Memory |
|---|---|---|
First App Load | 24.4 s | 465‑473 MB |
Subsequent App Load | 198 ms | 329‑348 MB |
Inference | 216 ms | 12‑28 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