|View source on GitHub|
tfp.experimental.substrates.numpy.math.log_combinations( n, counts, name='log_combinations' )
counts has last dimension
k, we compute
the multinomial coefficient as:
n! / sum_i n_i!
i runs over all
counts. This represents
n. This represents counts in
kis the last dimension of the tensor.
name: A name for this operation (optional).
Tensorrepresenting the multinomial coefficient between