Profile Job Results
Jobs
jgl2kkvlp
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
: uint8[1, 520, 520, 3]Completion Time
7/20/2025, 1:03:13 AM
Options
--compute_unit gpu
Versions
- TensorFlow Lite: 2.17.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.07.12.0
Estimated Inference Time
770 ms
Estimated Peak Memory Usage
27 ‑ 60 MB
Compute Units
GPU
100
CPU
2
Stage | Time | Memory |
---|---|---|
First App Load | 1.43 min | 439‑447 MB |
Subsequent App Load | 1.80 min | 465‑512 MB |
Inference | 770 ms | 27‑60 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