Profile Job Results
Jobs
jgkqyyeog
Results Ready
Name
deeplabv3_resnet50
Target Device
- QCS8250 (Proxy)
- Android 12
- Qualcomm® QCS8250
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 gpuVersions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.07.12.0
Estimated Inference Time
802 ms
Estimated Peak Memory Usage
2 ‑ 233 MB
Compute Units
GPU
100
CPU
2
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.93 min | 503‑504 MB |
Subsequent App Load | 1.83 min | 505‑507 MB |
Inference | 802 ms | 2‑233 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