chainer.initializers.DownsamplingConvFilter

class chainer.initializers.DownsamplingConvFilter(interpolation='linear', dtype=None)

Initializes array with downsampling filter.

The array is initialized with a standard image downsampling weight. This initializer is often used as initial weight for ConvolutionND(). ConvolutionND() is expected that its stride is equal to (ksize + 1) // 2.

Reference: Long et al., https://arxiv.org/abs/1411.4038

Variables

• ~DownsamplingConvFilter.interpolation (str) – Downsampling interpolation method.

• 'linear'. (Default is) –

Methods

__call__(array)

Initializes given array.

This method destructively changes the value of array. The derived class is required to implement this method. The algorithms used to make the new values depend on the concrete derived classes.

Parameters

array (N-dimensional array) – An array to be initialized by this initializer.

__eq__(value, /)

Return self==value.

__ne__(value, /)

Return self!=value.

__lt__(value, /)

Return self<value.

__le__(value, /)

Return self<=value.

__gt__(value, /)

Return self>value.

__ge__(value, /)

Return self>=value.