Module prelude Copy item path Source pub use super::Loss ;pub use super::NdMask ;pub use super::Model ;pub use super::direction::FftDirection ;pub use super::mode::FftMode ;pub use super::plan::FftPlan ;pub use super::DFT ;pub use super::propagate::Propagate ;pub use super::shape::ModelShape ;pub use super::NdResult ;pub use super::Result ;pub use super::kinds ::*;pub use super::binary ::*;pub use super::linear ::*;pub use super::nl ::*;pub use super::avg ::*;pub use super::lecun ::*;pub use super::trunc ::*;pub use super::xavier ::*;pub use super::traits ::*;pub use super::dropout ::*;pub use super::error ::*;pub use super::config ::*;pub use super::module ::*;pub use super::num ::*;pub use super::ops ::*;pub use super::predict ::*;pub use super::setup ::*;pub use super::train ::*;consts Error Fft Mask Padding PadAction PadMode D_MODEL The default model size for any given model EPSILON The default epsilon value for floating point operations Affine ArrayLike Decrement Decrement generally describes an object capable of decrementing itself; DefaultLike Entry FillLike Increment Initialize This trait provides the base methods required for initializing an ndarray with random values.
Initialize is similar to RandomExt , however, it focuses on flexibility while implementing additional
features geared towards machine-learning models; such as lecun_normal initialization. InitializeExt This trait extends the Initialize trait with methods for generating random arrays from various distributions. IntoAxis Inverse IsSquare MaskFill This trait is used to fill an array with a value based on a mask.
The mask is a boolean array of the same shape as the array. Matmul Matpow NdLike OfType OnesLike OrInsert Pad Sequence A trait for sequential data structures;
This trait is implemented for iterators that have a known length. SequenceIter Store SummaryStatistics This trait describes the fundamental methods of summary statistics.
These include the mean, standard deviation, variance, and more. Toggle Unsqueeze ZerosLike concat_iter Creates an n-dimensional array from an iterator of n dimensional arrays. fft Computes the Fast Fourier Transform of a one-dimensional, complex-valued signal. floor_div genspace hstack ifft Computes the Inverse Fast Fourier Transform of an one-dimensional, complex-valued signal. inverse irfft Computes the Inverse Fast Fourier Transform of an one-dimensional, real-valued signal.
TODO: Fix the function; currently fails to compute the correct result linarr linspace mae A functional implementation of the mean absolute error loss function which compares two similar
arrays mse A functional implementation of the mean squared error loss function that compares two similar
arrays pad pad_to randc Generate a random array of complex numbers with real and imaginary parts in the range [0, 1) rangespace creates a matrix from the given shape filled with numerical elements [0, n) spaced evenly by 1 rfft Computes the Fast Fourier Transform of an one-dimensional, real-valued signal.
TODO: Optimize the function to avoid unnecessary computation. round_to Round the given value to the given number of decimal places. stack_iter Creates a larger array from an iterator of smaller arrays. stdnorm Given a shape, generate a random array using the StandardNormal distribution stdnorm_from_seed tril Returns the lower triangular portion of a matrix. triu Returns the upper triangular portion of a matrix. uniform_from_seed Creates a random array from a uniform distribution using a given key vstack BoxError A type alias for a boxed Error type that is Send, Sync, and 'static. BoxResult A type alias for a boxed Result which returns some object, T, and uses a BoxError as the error type.