Profile Job Results
Jobs
jpxkjke15
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, 520, 520, 3]Completion Time
1/21/2025, 4:42:13 PM
Options
--compute_unit gpu
Versions
- TensorFlow Lite: 2.17.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.01.04.0
Estimated Inference Time
294 ms
Estimated Peak Memory Usage
0 ‑ 200 MB
Compute Units
GPU
98
CPU
2
Stage | Time | Memory |
---|---|---|
First App Load | 36.3 s | 486‑488 MB |
Subsequent App Load | 35.9 s | 452‑455 MB |
Inference | 294 ms | 0‑200 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