tf.compat.v2.nn.dilation2d

View source on GitHub

Computes the grayscale dilation of 4-D input and 3-D filters tensors.

tf.compat.v2.nn.dilation2d(
    input, filters, strides, padding, data_format, dilations, name=None
)

The input tensor has shape [batch, in_height, in_width, depth] and the filters tensor has shape [filter_height, filter_width, depth], i.e., each input channel is processed independently of the others with its own structuring function. The output tensor has shape [batch, out_height, out_width, depth]. The spatial dimensions of the output tensor depend on the padding algorithm. We currently only support the default "NHWC" data_format.

In detail, the grayscale morphological 2-D dilation is the max-sum correlation (for consistency with conv2d, we use unmirrored filters):

output[b, y, x, c] =
   max_{dy, dx} input[b,
                      strides[1] * y + rates[1] * dy,
                      strides[2] * x + rates[2] * dx,
                      c] +
                filters[dy, dx, c]

Max-pooling is a special case when the filter has size equal to the pooling kernel size and contains all zeros.

Note on duality: The dilation of input by the filters is equal to the negation of the erosion of -input by the reflected filters.