Separable convolution consists of first performing
a depthwise spatial convolution
(which acts on each input channel separately)
followed by a pointwise convolution which mixes together the resulting
output channels. The depthMultiplier argument controls how many
output channels are generated per input channel in the depthwise step.
Intuitively, separable convolutions can be understood as
a way to factorize a convolution kernel into two smaller kernels,
or as an extreme version of an Inception block.
Input shape:
4D tensor with shape:
[batch, channels, rows, cols] if data_format='channelsFirst'
or 4D tensor with shape:
[batch, rows, cols, channels] if data_format='channelsLast'.
Output shape:
4D tensor with shape:
[batch, filters, newRows, newCols] if data_format='channelsFirst'
or 4D tensor with shape:
[batch, newRows, newCols, filters] if data_format='channelsLast'.
rows and cols values might have changed due to padding.
Depthwise separable 2D convolution.
Separable convolution consists of first performing a depthwise spatial convolution (which acts on each input channel separately) followed by a pointwise convolution which mixes together the resulting output channels. The
depthMultiplierargument controls how many output channels are generated per input channel in the depthwise step.Intuitively, separable convolutions can be understood as a way to factorize a convolution kernel into two smaller kernels, or as an extreme version of an Inception block.
Input shape: 4D tensor with shape:
[batch, channels, rows, cols]if data_format='channelsFirst' or 4D tensor with shape:[batch, rows, cols, channels]if data_format='channelsLast'.Output shape: 4D tensor with shape:
[batch, filters, newRows, newCols]if data_format='channelsFirst' or 4D tensor with shape:[batch, newRows, newCols, filters]if data_format='channelsLast'.rowsandcolsvalues might have changed due to padding.