Profile Job Results
Jobs
jgj7exj1g
Results Ready
Name
detectron2_detection_roi_head
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
features: float32[1, 50, 50, 1024]proposals_boxes: float32[1, 200, 4]Completion Time
8/22/2026, 11:14:25 AM
Versions
- Lite RT: 1.4.5
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.08.14.0
Estimated Inference Time
2.26 s
Estimated Peak Memory Usage
0 ‑ 4 GB
Compute Units
CPU
105
GPU
61
| Stage | Time | Memory |
|---|---|---|
First App Load | 17.2 min | 1 GB |
Subsequent App Load | 3.47 s | 20‑21 MB |
Inference | 2.26 s | 0‑4 GB |
| Lite RT | 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 |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device