Profile Job Results
Jobs
jz5wr8wmp
Results Ready
Name
deeplabv3_resnet50
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 513, 513, 3]Completion Time
8/27/2024, 9:15:40 AM
Options
--compute_unit gpuVersions
- TensorFlow Lite: 2.16.1
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.08.23.0
Estimated Inference Time
294 ms
Estimated Peak Memory Usage
0 - 170 MB
Compute Units
GPU
95
| Stage | Time | Memory |
|---|---|---|
First App Load | 37.4 s | 531-532 MB |
Subsequent App Load | 518 ms | 327-393 MB |
Inference | 294 ms | 0-170 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