WOLFRAM

Wolfram Language & System Documentation Center
Wolfram Language Home Page »

WLNet (.wlnet)

[Experimental]

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:

In[1]:=1
✖
https://wolfram.com/xid/0grcmwqm5ss-js14pr
Out[1]=1

Export this net to the WLNet format:

In[2]:=2
✖
https://wolfram.com/xid/0grcmwqm5ss-gsjvus
Out[2]=2

Import the net:

In[3]:=3
✖
https://wolfram.com/xid/0grcmwqm5ss-qyhcg5
Out[3]=3

Define an initialized NetGraph:

In[1]:=1
✖
https://wolfram.com/xid/0grcmwqm5ss-k1c3za
Out[1]=1

Export the net along with its initialized parameters:

In[2]:=2
✖
https://wolfram.com/xid/0grcmwqm5ss-4vp440
Out[2]=2

Import the network:

In[3]:=3
✖
https://wolfram.com/xid/0grcmwqm5ss-64xf9
Out[3]=3

Evaluate the net on input data:

In[4]:=4
✖
https://wolfram.com/xid/0grcmwqm5ss-fh8h6o
Out[4]=4

This is equivalent to evaluating the original net:

In[5]:=5
✖
https://wolfram.com/xid/0grcmwqm5ss-n6e0iw
Out[5]=5

Import a version of the net without any initialized arrays:

In[6]:=6
✖
https://wolfram.com/xid/0grcmwqm5ss-wbosbw
Out[6]=6

Import an association of arrays:

In[7]:=7
✖
https://wolfram.com/xid/0grcmwqm5ss-zy4wqm
Out[7]=7