Layer Object

Back to Home

Import

const Layer = require('dannjs').layer;

Contructor( type , inputSize , sampleSize , stride )

When you create a pooling layer you need to specify the number of input size, the sample size & the stride.

const l1 = new Layer('avgpool',16,2,2);

Object Properties

• type
  

  A string representing the type of this layer.

• subtype
  

  A string representing the sub type of this layer. Can be 'pool' for pooling layers or 'input', 'hidden' and 'output' for neuron layers used by Dann models.

• sampleSize
  

  The size of the 2d sample iterating trough the array.

• stride
  

  The number of jumps the sample is going to perform for each iteration.

• poolfunc
  

  The function this pooling layer uses to process a sample as an array into a numeric output. ex: avg, max. See available pooling functions Here.
  
  
  

Functions

• feed