Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp3jk31lg
Results Ready
Name
posenet_mobilenet_quantized
Target Device
  • QCS8250 (Proxy)
  • Android 12
  • Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 513, 257, 3]
Completion Time
1/21/2025, 1:08:56 PM
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 11 (RP1A.200720.012)
  • AI Hub: aihub-2025.01.04.0
Estimated Inference Time
13.6 ms
Estimated Peak Memory Usage
0 ‑ 8 MB
Compute Units
NPU
45
GPU
3
StageTimeMemory
First App Load
492 ms6‑8 MB
Subsequent App Load
186 ms6‑8 MB
Inference
13.6 ms0‑8 MB
TensorFlow LiteValue
number_of_threads4
NNAPI DelegateValue
accelerator_name"qti-dsp"
execution_preferencekSustainedSpeed
allow_fp16true
GPUv2 DelegateValue
inference_preferenceTFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED
inference_priority1TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY
inference_priority2TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE
inference_priority3TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION

Sign up to run this model on a hosted Qualcomm® device!

Run on device