LBBNN (version 0.1.2)

RNVP_layer: Single RNVP transform layer.

Description

Affine half flow aka Real Non-Volume Preserving (x = z * exp(s) + t), where a randomly selected half z1 of the dimensions in z are transformed as an Affine function of the other half z2, i.e. scaled by s(z2) and shifted by t(z2). From "Density estimation using Real NVP", Dinh et al. (May 2016) https://arxiv.org/abs/1605.08803 This implementation uses the numerically stable updates introduced by IAF: https://arxiv.org/abs/1606.04934

Usage

RNVP_layer(hidden_sizes, device = "cpu")

Value

A torch::nn_module object representing a single RNVP layer. The module has the following methods:

forward(z)

Applies the RNVP transformation. Returns a torch::torch_tensor with the same shape as z.

log_det()

A scalar torch::torch_tensor giving the log-determinant of the Jacobian of the transformation.

Arguments

hidden_sizes

A vector of integers. The first is the dimensionality of the vector, to be transformed by RNVP. The subsequent are hidden dimensions in the MLP.

device

The device to be used. Default is CPU.

Examples

# \donttest{
z <- torch::torch_rand(200)
layer <- RNVP_layer(c(200,50,100))
out <- layer(z)
print(dim(out))
print(layer$log_det())
# }