Profile Job Results
Jobs
jgnl6rem5
Results Ready
Name
yolov7
Target Device
- QCS8250 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 640, 640, 3]Completion Time
4/8/2025, 12:01:33 PM
Versions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.03.24.0
Estimated Inference Time
55.9 ms
Estimated Peak Memory Usage
15 ‑ 55 MB
Compute Units
GPU
146
CPU
82
| Stage | Time | Memory |
|---|---|---|
First App Load | 162 min | 75‑77 MB |
Subsequent App Load | 157 min | 68‑70 MB |
Inference | 55.9 s | 15‑55 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 |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device