Profile Job Results
Jobs
jg9lk30wg
Results Ready
Name
yolov8_det_quantized
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
11/26/2024, 3:45:37 PM
Versions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
46.7 ms
Estimated Peak Memory Usage
3 ‑ 24 MB
Compute Units
NPU
279
GPU
1
| Stage | Time | Memory |
|---|---|---|
First App Load | 710 ms | 3‑4 MB |
Subsequent App Load | 356 ms | 5‑18 MB |
Inference | 46.7 ms | 3‑24 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| NNAPI Delegate | Value |
|---|---|
| accelerator_name | "qti-dsp" |
| execution_preference | kSustainedSpeed |
| allow_fp16 | true |
| 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