|TensorFlow 1 version||View source on GitHub|
Atrous convolution (a.k.a. convolution with holes or dilated convolution).
Compat aliases for migration
See Migration guide for more details.
tf.nn.atrous_conv2d( value, filters, rate, padding, name=None )
This function is a simpler wrapper around the more general
tf.nn.convolution, and exists only for backwards compatibility. You can
tf.nn.convolution to perform 1-D, 2-D, or 3-D atrous convolution.
Computes a 2-D atrous convolution, also known as convolution with holes or
dilated convolution, given 4-D
filters tensors. If the
parameter is equal to one, it performs regular 2-D convolution. If the
parameter is greater than one, it performs convolution with holes, sampling
the input values every
rate pixels in the
This is equivalent to convolving the input with a set of upsampled filters,
produced by inserting
rate - 1 zeros between two consecutive values of the
filters along the
width dimensions, hence the name atrous
convolution or convolution with holes (the French word trous means holes in