Features & Scope of support

NetsPresso Model Searcher

NetsPresso Model Searcher automatically searches optimized models for your target device

Key Features


  • Automate time-consuming and repetitive AI model development tasks
  • The infrastructure is ready so that anyone can start developing the model right away, and it includes a retraining pipeline for experts.


  • Create multiple models within the search space using the Neural Architecture Search
  • With one project execution, it is possible to obtain model results that meet various purposes such as performance and trade-off

HW aware Model Searcher

  • Benchmarks can be created on the actual device without setting the device
  • Develop a model that meets the target latency according to the device


Scope of support


  • Computer Vision - Image Classification
  • Computer Vision - Object Detection
  • Computer Vision - Semantic Segmentation

Output model frameworks

  • TensorRT
  • TensorFlow Lite
  • OpenVINO


  • NVIDIA Jetson family (Nano, TX2, Xavier NX, AGX Xavier, AGX Orin)
  • Raspberry Pi series (3B+, 4B)
  • Intel Xeon W-2223
  • Arm Virtual Hardware (Corstone 300 (U65))