|View source on GitHub|
Applies euclidean distance transform(s) to the image(s).
tfa.image.euclidean_dist_transform( images, dtype=tf.float32, name=None )
images: A tensor of shape (num_images, num_rows, num_columns, 1) (NHWC), or (num_rows, num_columns, 1) (HWC) or (num_rows, num_columns) (HW).
dtype: DType of the output tensor.
name: The name of the op.
Image(s) with the type
dtype and same shape as
images, with the
transform applied. If a tensor of all ones is given as input, the
output tensor will be filled with the max value of the
imageis not tf.uint8, or
dtypeis not floating point.
imagemore than one channel, or
imageis not of rank between 2 and 4.