eIQ Transfer Learning Lab with i.MX 8

Document created by Vanessa Maegima Employee on Jul 4, 2019Last modified by Raluca Popa on Dec 5, 2019
Version 4Show Document
  • View in full screen mode
This lab will take an existing TensorFlow image classification model and re-train it to categorize images of flowers. This is known as transfer learning. This updated model will then be converted into a TensorFlow Lite file. By using that file with the TensorFlow Lite inference engine that is part of NXPs eIQ package, the model can be ran on an i.MX 8QM-MEK board. This lab can also be used with different i.MX 8 devices.
Please check attached pdf's:
  • 'eIQ Transfer Learning Lab iMX8.pdf': detailed lab instructions
  • 'TransferLearningOverview.pdf': theoretical background of transfer learning and results for customized data set.
Please check also: eIQ Transfer Learning Lab with i.MX RT.
1 person found this helpful