Thanks for tuning in to Google I/O. View all sessions on demandWatch on demand

tfg.image.matting.reconstruct

Reconstruct the matte from the image using the linear coefficients.

tfg.image.matting.reconstruct(
    image: type_alias.TensorLike,
    coeff_mul: type_alias.TensorLike,
    coeff_add: type_alias.TensorLike,
    name: str = 'matting_reconstruct'
) -> tf.Tensor

Reconstruct the matte from the image using the linear coefficients (a, b) returned by the linear_coefficients function.

image A tensor of shape [B, H, W, C] .
coeff_mul A tensor of shape [B, H, W, C] representing the multiplicative part of the linear coefficients.
coeff_add A tensor of shape [B, H, W, 1] representing the additive part of the linear coefficients.
name A name for this op. Defaults to "matting_reconstruct".

A tensor of shape [B, H, W, 1] containing the mattes.

ValueError If image, coeff_mul, or coeff_add are not of rank 4. If the last dimension of coeff_add is not 1. If the batch dimensions of image, coeff_mul, and coeff_add do not match.