numpy_utils

Functions

inverse_shifted_softplus(x[, shift, beta, ...])	Inverse of the shifted softplus function.
inverse_sigmoid(x)	Inverse of the sigmoid function.
inverse_softplus(x[, beta, threshold])	Numerically stabilized inverse softplus function.
one_hot(indices, num_classes[, dtype])	Converts a 1D array of indices to a one-hot encoded 2D array.
shifted_softplus(x[, beta, threshold, shift])	Shifted version of the softplus function such that shifted_softplus(0) = 1
softplus(x[, beta, threshold])	Numerically stabilized softplus function.