Computes the grayscale erosion of 4-D value and 3-D filters tensors.

The value tensor has shape [batch, in_height, in_width, depth] and the filters tensor has shape [filters_height, filters_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 erosion is given by:

output[b, y, x, c] =
   min_{dy, dx} value[b,
                      strides[1] * y - dilations[1] * dy,
                      strides[2] * x - dilations[2] * dx,
                      c] -
                filters[dy, dx, c]

Duality: The erosion of value by the filters is equal to the negation of the dilation of -value by the reflected filters.

value A Tensor. 4-D with shape [batch, in_height, in_width, depth].
filters A Tensor. Must have the same type as value. 3-D with shape [filters_height, filters_width, depth].
strides A list of ints that has length >= 4. 1-D of length 4. The stride of the sliding window for each dimension of the input tensor. Must be: [1, stride_height, s