Profile Job Results
Jobs
jp04j109g
Results Ready
Name
resnet_2plus1d_quantized
Target Device
- QCS8250 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
video: uint8[1, 16, 112, 112, 3]Completion Time
3/11/2025, 10:03:39 PM
Versions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.03.06.0
Estimated Inference Time
1.09 s
Estimated Peak Memory Usage
427 ‑ 461 MB
Compute Units
CPU
167
GPU
3
| Stage | Time | Memory |
|---|---|---|
First App Load | 291 ms | 20‑21 MB |
Subsequent App Load | 165 ms | 66‑68 MB |
Inference | 1.09 s | 427‑461 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