Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Mask2Former

Profile Job Results

Jobs
jpr8vwoe5
Results Ready
Name
mask2former
Target Device
  • SA8650 (Proxy)
  • Android 13
  • Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 384, 384, 3]
Completion Time
4/8/2025, 3:47:24 PM
Options
--compute_unit cpu
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2025.03.24.0
Estimated Inference Time
1.44 s
Estimated Peak Memory Usage
138 ‑ 166 MB
Compute Units
CPU
3208
StageTimeMemory
First App Load
197 ms328‑330 MB
Subsequent App Load
164 ms246‑253 MB
Inference
1.44 s138‑166 MB
TensorFlow LiteValue
number_of_threads4
XNNPACK DelegateValue

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

Run on device