tfb_transpose: Computes'Y = g(X) = transpose_rightmost_dims(X,...

In tfprobability: Interface to 'TensorFlow Probability'

ComputesY = g(X) = transpose_rightmost_dims(X, rightmost_perm)

Description

This bijector is semantically similar to tf.transpose except that it transposes only the rightmost "event" dimensions. That is, unlike tf$transpose the perm argument is itself a permutation of tf$range(rightmost_transposed_ndims) rather than tf$range(tf$rank(x)), i.e., users specify the (rightmost) dimensions to permute, not all dimensions.

Usage

tfb_transpose(
  perm = NULL,
  rightmost_transposed_ndims = NULL,
  validate_args = FALSE,
  name = "transpose"
)

Arguments

perm	Positive integer vector-shaped Tensor representing permutation of rightmost dims (for forward transformation). Note that the 0th index represents the first of the rightmost dims and the largest value must be rightmost_transposed_ndims - 1 and corresponds to tf$rank(x) - 1. Only one of perm and rightmost_transposed_ndims can (and must) be specified. Default value: tf$range(start=rightmost_transposed_ndims, limit=-1, delta=-1).
rightmost_transposed_ndims	Positive integer scalar-shaped Tensor representing the number of rightmost dimensions to permute. Only one of perm and rightmost_transposed_ndims can (and must) be specified. Default value: tf$size(perm).
validate_args	Logical, default FALSE. Whether to validate input with asserts. If validate_args is FALSE, and the inputs are invalid, correct behavior is not guaranteed.
name	name prefixed to Ops created by this class.

Details

The actual (forward) transformation is:

sample_batch_ndims <- tf$rank(x) - tf$size(perm) perm = tf$concat(list(tf$range(sample_batch_ndims), sample_batch_ndims + perm),axis=0) tf$transpose(x, perm)

Value

a bijector instance.

See Also

For usage examples see tfb_forward(), tfb_inverse(), tfb_inverse_log_det_jacobian().

Other bijectors: tfb_absolute_value(), tfb_affine_linear_operator(), tfb_affine_scalar(), tfb_affine(), tfb_ascending(), tfb_batch_normalization(), tfb_blockwise(), tfb_chain(), tfb_cholesky_outer_product(), tfb_cholesky_to_inv_cholesky(), tfb_correlation_cholesky(), tfb_cumsum(), tfb_discrete_cosine_transform(), tfb_expm1(), tfb_exp(), tfb_ffjord(), tfb_fill_scale_tri_l(), tfb_fill_triangular(), tfb_glow(), tfb_gompertz_cdf(), tfb_gumbel_cdf(), tfb_gumbel(), tfb_identity(), tfb_inline(), tfb_invert(), tfb_iterated_sigmoid_centered(), tfb_kumaraswamy_cdf(), tfb_kumaraswamy(), tfb_lambert_w_tail(), tfb_masked_autoregressive_default_template(), tfb_masked_autoregressive_flow(), tfb_masked_dense(), tfb_matrix_inverse_tri_l(), tfb_matvec_lu(), tfb_normal_cdf(), tfb_ordered(), tfb_pad(), tfb_permute(), tfb_power_transform(), tfb_rational_quadratic_spline(), tfb_rayleigh_cdf(), tfb_real_nvp_default_template(), tfb_real_nvp(), tfb_reciprocal(), tfb_reshape(), tfb_scale_matvec_diag(), tfb_scale_matvec_linear_operator(), tfb_scale_matvec_lu(), tfb_scale_matvec_tri_l(), tfb_scale_tri_l(), tfb_scale(), tfb_shifted_gompertz_cdf(), tfb_shift(), tfb_sigmoid(), tfb_sinh_arcsinh(), tfb_sinh(), tfb_softmax_centered(), tfb_softplus(), tfb_softsign(), tfb_split(), tfb_square(), tfb_tanh(), tfb_transform_diagonal(), tfb_weibull_cdf(), tfb_weibull()

tfprobability documentation built on Sept. 1, 2022, 5:07 p.m.