Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Unet-Segmentation

Profile Job Results

Jobs
jgonejjqp
Results Ready
Name
unet_segmentation
Target Device
  • QCS8250 (Proxy)
  • Android 12
  • Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 640, 1280, 3]
Completion Time
8/2/2025, 3:08:31 PM
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 11 (RP1A.200720.012)
  • AI Hub: aihub-2025.07.25.0
Estimated Inference Time
3.13 s
Estimated Peak Memory Usage
0 ‑ 846 MB
Compute Units
NPU
38
StageTimeMemory
First App Load
667 ms3‑5 MB
Subsequent App Load
386 ms3‑5 MB
Inference
3.13 s0‑846 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