Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
BiseNet

Profile Job Results

Jobs
j56z11d6g
Results Ready
Name
bisenet
Target Device
  • QCS8250 (Proxy)
  • Android 12
  • Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 720, 960, 3]
Completion Time
7/20/2025, 2:01:46 AM
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 11 (RP1A.200720.012)
  • AI Hub: aihub-2025.07.12.0
Estimated Inference Time
291 ms
Estimated Peak Memory Usage
8 ‑ 10 MB
Compute Units
NPU
68
StageTimeMemory
First App Load
502 ms0‑3 MB
Subsequent App Load
151 ms0‑3 MB
Inference
291 ms8‑10 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