Machine Learning for Images

Mathematica 12: Machine Learning for Images

Version 12 image processing and computer vision use extensively updated machine learning and neural net capabilities and introduce several built-in, high-level functions for object recognition, face analysis, restyling and more. In addition, with a growing number of pre-trained networks available from the Wolfram Neural Net Repository, one can use available pre-trained networks immediately, or manipulate and reassemble them to train on new data. Powerful network surgery capabilities enable transfer learning, which allows for solving problems using much smaller datasets.

Mathematica 12: Machine Learning for Images
  • Built-in image style transfer using one or more templates. »
  • Expanded built-in computer vision functions. »
  • Automated object detection and recognition. »
  • Significantly improved face detection. »
  • Built-in facial age, gender, emotion estimation. »
  • Immediately accessible trained and untrained neural nets. »
  • Efficient and customizable image net encoders and decoders. »
  • Extensive support for neural net dissection and reassembly. »
  • Advanced neural net measurement and analysis. »
  • GPU accelerated neural net training and evaluation. »
  • Improved text recognition through customizable settings. »

Related Examples