Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
HRNetPoseQuantized

Profile Job Results

Jobs
jpeedyjop
Results Ready
Name
hrnet_pose
Target Device
  • QCS8250 (Proxy)
  • Android 12
  • Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 256, 192, 3]
Completion Time
4/8/2025, 4:27:04 PM
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 11 (RP1A.200720.012)
  • AI Hub: aihub-2025.03.24.0
Estimated Inference Time
17.2 s
Estimated Peak Memory Usage
0 ‑ 2 MB
Compute Units
NPU
518
StageTimeMemory
First App Load
82.7 min4‑6 MB
Subsequent App Load
76.9 min3‑5 MB
Inference
17.2 s0‑2 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