WOLFRAM

Background & Context

    • Used for storing trained and untrained neural nets.
    • Binary format.
    • Developed at Wolfram Research.

Import & Export

Import Elements

  • General Import elements:
  • "Elements" list of elements and options available in this file
    "Summary"summary of the file
    "Rules"list of rules for all available elements
  • Import elements include:
  • "Net"the net, including all initialized arrays
    "UninitializedNet"the net, without any arrays
    "ArrayList"parameter arrays as a list
    "ArrayAssociation"parameter arrays as an association
    "WLVersion"version of the Wolfram Language used to create the file

Examples

Basic Examples  (2)Summary of the most common use cases

Define a NetChain:

Out[1]=1

Export this net to the WLNet format:

Out[2]=2

Import the net:

Out[3]=3

Define an initialized NetGraph:

Out[1]=1

Export the net along with its initialized parameters:

Out[2]=2

Import the network:

Out[3]=3

Evaluate the net on input data:

Out[4]=4

This is equivalent to evaluating the original net:

Out[5]=5

Import a version of the net without any initialized arrays:

Out[6]=6

Import an association of arrays:

Out[7]=7