Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Person-Foot-Detection

Profile Job Results

Jobs
j57l3k1lg
Results Ready
Name
foot_track_net_w8a8
Target Device
  • QCS8250 (Proxy)
  • Android 12
  • Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 480, 640, 3]
Completion Time
10/5/2025, 6:03:02 PM
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 11 (RP1A.200720.012)
  • AI Hub: aihub-2025.09.26.0
Estimated Inference Time
26.7 ms
Estimated Peak Memory Usage
1 ‑ 4 MB
Compute Units
NPU
141
StageTimeMemory
First App Load
373 ms1‑3 MB
Subsequent App Load
241 ms1‑3 MB
Inference
26.7 ms1‑4 MB
TensorFlow LiteValue
number_of_threads4
NNAPI DelegateValue
accelerator_name"qti-dsp"
execution_preferencekSustainedSpeed
allow_fp16true

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

Run on device