Skip to content

Wrong kernel size in lowest level posterior of PHiSeg #29

@baumgach

Description

@baumgach

In PHiSeg Posterior for lowest level

mu[i] = layers.conv2D(pre_z[i+resolution_levels-latent_levels], 'z%d_mu' % i, num_filters=zdim_0, activation=tf.identity)

should be convolutions with kernel=(1,1)

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions