Profile Job Results
Jobs
jgn6y64j5
Results Ready
Name
yolov7_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
1/21/2025, 3:31:56 PM
Versions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.01.04.0
Estimated Inference Time
56.2 ms
Estimated Peak Memory Usage
15 ‑ 54 MB
Compute Units
GPU
146
CPU
82
Stage | Time | Memory |
---|---|---|
First App Load | 9.88 s | 74‑76 MB |
Subsequent App Load | 9.35 s | 71‑73 MB |
Inference | 56.2 ms | 15‑54 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