Skip to content

Why sampling from a multinomial distribution? #3

@pyun-ram

Description

@pyun-ram

Hi @ariseff , thanks for sharing the awesome code repo! :)
Your code works well, but I cannot understand why we need to do sampling from a multinomial distribution?
Can we replace it with argmax or just with no-sampling?

class_ind = tf.to_int32(tf.multinomial(tf.log(probs), 1)[0][0])

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