Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jgz38jv45
Results Ready
Name
mediapipe_face_quantized_MediaPipeFaceDetector
Target Device
  • QCS6490 (Proxy)
  • Android 12
  • Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 256, 256, 3]
Completion Time
11/26/2024, 12:23:16 PM
Versions
  • TensorFlow Lite: 2.17.0
  • QNN TfLite Delegate: v2.28.2.241116104011_103376
  • Android: 12 (SP1A.210812.016)
  • AI Hub: aihub-2024.11.22.0
Estimated Inference Time
765 μs
Estimated Peak Memory Usage
0 ‑ 19 MB
Compute Units
NPU
121
StageTimeMemory
First App Load
963 ms40‑49 MB
Subsequent App Load
976 ms10‑36 MB
Inference
765 μs0‑19 MB
TensorFlow LiteValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.useConvHmxtrue

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

Run on device