torch

Class representing the context.

Abstract base class for constraints.

Generic R6 class representing distributions

Converts to array

Computes the sum of gradients of given tensors w.r.t. graph leaves.

Records operation history and defines formulas for differentiating ops.

Computes and returns the sum of gradients of outputs w.r.t. the inputs.

Set grad mode

MKL is available

MKLDNN is available

OpenMP is available

Given a list of values (possibly containing numbers), returns a list where each value is broadcasted based on the following rules:

Returns the index of a currently selected device.

Returns the number of GPUs available.

Returns a bool indicating if CUDA is currently available.

Data loader. Combines a dataset and a sampler, and provides single- or multi-process iterators over the dataset.

Creates an iterator from a DataLoader

Get the next element of a dataloader iterator

Helper function to create an R6 class that inherits from the abstract Dataset class

Dataset Subset

Gets and sets the default floating point dtype.

Creates a Bernoulli distribution parameterized by probs or logits (but not both). Samples are binary (0 or 1). They take the value 1 with probability p and 0 with probability 1 - p.

Creates a Chi2 distribution parameterized by shape parameter df. This is exactly equivalent to distr_gamma(alpha=0.5*df, beta=0.5)

Creates a Gamma distribution parameterized by shape concentration and rate.

Creates a normal (also called Gaussian) distribution parameterized by loc and scale.

Creates a Poisson distribution parameterized by rate, the rate parameter.

Enumerate an iterator

Enumerate an iterator

List of files to download

Install Torch

Install Torch from files

Checks if the object is a dataloader

Checks if the object is a nn_buffer

Checks if the object is an nn_module

Checks if an object is a nn_parameter

Checks if the object is a torch optimizer

Checks if object is a device

Check if object is a torch data type

Check if an object is a torch layout.

Check if an object is a memory format

Checks if an object is a QScheme

Checks if a tensor is undefined

Loads a script_function or script_module previously saved with jit_save

Saves a script_function to a path

Trace a function and return an executable script_function.

Load a state dict file

Sets the learning rate of each parameter group to the initial lr times a given function. When last_epoch=-1, sets initial lr as lr.

Multiply the learning rate of each parameter group by the factor given in the specified function. When last_epoch=-1, sets initial lr as lr.

Once cycle learning rate

Creates learning rate schedulers

Step learning rate decay

Applies a 1D adaptive average pooling over an input signal composed of several input planes.

Applies a 2D adaptive average pooling over an input signal composed of several input planes.

Applies a 3D adaptive average pooling over an input signal composed of several input planes.

AdaptiveLogSoftmaxWithLoss module

Applies a 1D adaptive max pooling over an input signal composed of several input planes.

Applies a 2D adaptive max pooling over an input signal composed of several input planes.

Applies a 3D adaptive max pooling over an input signal composed of several input planes.

Applies a 1D average pooling over an input signal composed of several input planes.

Applies a 2D average pooling over an input signal composed of several input planes.

Applies a 3D average pooling over an input signal composed of several input planes.

BatchNorm1D module

BatchNorm2D

BatchNorm3D

Binary cross entropy loss

BCE with logits loss

Bilinear module

Creates a nn_buffer

CELU module

Sparsemax activation

Conv1D module

Conv2D module

Conv3D module

ConvTranspose1D

ConvTranpose2D module

ConvTranpose3D module

Cosine embedding loss

CrossEntropyLoss module

The Connectionist Temporal Classification loss.

Dropout module

Dropout2D module

Dropout3D module

ELU module

Embedding module

Applies a 2D fractional max pooling over an input signal composed of several input planes.

Applies a 3D fractional max pooling over an input signal composed of several input planes.

GELU module

GLU module

Group normalization

Applies a multi-layer gated recurrent unit (GRU) RNN to an input sequence.

Hardshwink module

Hardsigmoid module

Hardswish module

Hardtanh module

Hinge embedding loss

Identity module

Calculate gain

Constant initialization

Dirac initialization

Eye initialization

Kaiming normal initialization

Kaiming uniform initialization

Normal initialization

Ones initialization

Orthogonal initialization

Sparse initialization

Truncated normal initialization

Uniform initialization

Xavier normal initialization

Xavier uniform initialization

Zeros initialization

Kullback-Leibler divergence loss

L1 loss

Layer normalization

LeakyReLU module

Linear module

LogSigmoid module

LogSoftmax module

Applies a 1D power-average pooling over an input signal composed of several input planes.

Applies a 2D power-average pooling over an input signal composed of several input planes.

Applies a multi-layer long short-term memory (LSTM) RNN to an input sequence.

Margin ranking loss

MaxPool1D module

MaxPool2D module

Applies a 3D max pooling over an input signal composed of several input planes.

Computes a partial inverse of MaxPool1d.

Computes a partial inverse of MaxPool2d.

Computes a partial inverse of MaxPool3d.

Base class for all neural network modules.

Holds submodules in a list.

MSE loss

Multi margin loss

MultiHead attention

Multilabel margin loss

Multi label soft margin loss

Nll loss

Pairwise distance

Creates an nn_parameter

Poisson NLL loss

PReLU module

ReLU module

ReLu6 module

RNN module

RReLU module

SELU module

A sequential container

Sigmoid module

Smooth L1 loss

Soft margin loss

Softmax module

Softmax2d module

Softmin

Softplus module

Softshrink module

Softsign module

Tanh module

Tanhshrink module

Threshoold module

Triplet margin loss

Triplet margin with distance loss

Clips gradient norm of an iterable of parameters.

Clips gradient of an iterable of parameters at specified value.

Packs a Tensor containing padded sequences of variable length.

Packs a list of variable length Tensors

Pads a packed batch of variable length sequences.

Pad a list of variable length Tensors with padding_value

Adaptive_avg_pool1d

Adaptive_avg_pool2d

Adaptive_avg_pool3d

Adaptive_max_pool1d

Adaptive_max_pool2d

Adaptive_max_pool3d

Affine_grid

Alpha_dropout

Avg_pool1d

Avg_pool2d

Avg_pool3d

Batch_norm

Bilinear

Binary_cross_entropy

Binary_cross_entropy_with_logits

Celu

Sparsemax

Conv1d

Conv2d

Conv3d

Conv_tbc

Conv_transpose1d

Conv_transpose2d

Conv_transpose3d

Cosine_embedding_loss

Cosine_similarity

Cross_entropy

Ctc_loss

Dropout

Dropout2d

Dropout3d

Elu

Embedding

Embedding_bag

Fold

Fractional_max_pool2d

Fractional_max_pool3d

Gelu

Glu

Grid_sample

Group_norm

Gumbel_softmax

Hardshrink

Hardsigmoid

Hardswish

Hardtanh

Hinge_embedding_loss

Instance_norm

Interpolate

Kl_div

L1_loss

Layer_norm

Leaky_relu

Linear

Local_response_norm

Log_softmax

Logsigmoid

Lp_pool1d

Lp_pool2d

Margin_ranking_loss

Max_pool1d

Max_pool2d

Max_pool3d

Max_unpool1d

Max_unpool2d

Max_unpool3d

Mse_loss

Multi head attention forward

Multi_margin_loss

Multilabel_margin_loss

Multilabel_soft_margin_loss

Nll_loss

Normalize

One_hot

Pad

Pairwise_distance

Pdist

Pixel_shuffle

Poisson_nll_loss

Prelu

Relu

Relu6

Rrelu

Selu

Sigmoid

Smooth_l1_loss

Soft_margin_loss

Softmax

Softmin

Softplus

Softshrink

Softsign

Tanhshrink

Threshold

Triplet_margin_loss

Triplet margin with distance loss

Unfold

Adadelta optimizer

Adagrad optimizer

Implements Adam algorithm.

Averaged Stochastic Gradient Descent optimizer

LBFGS optimizer

Dummy value indicating a required value.

RMSprop optimizer

Implements the resilient backpropagation algorithm.

SGD optimizer

Creates a custom optimizer

Pipe operator

Re-exporting the as_iterator function.

Dataset wrapping tensors.

Number of threads

Abs

Absolute

Acos

Acosh

Adaptive_avg_pool1d

Add

Addbmm

Addcdiv

Addcmul

Addmm

Addmv

Addr

Allclose

Amax

Amin

Angle

Arange

Arccos

Arccosh

Arcsin

Arcsinh

Arctan

Arctanh

Argmax

Argmin

Argsort

As_strided

Asin

Asinh

Atan

Atan2

Atanh

Atleast_1d

Atleast_2d

Atleast_3d

Avg_pool1d

Baddbmm

Bartlett_window

Bernoulli

Bincount

Bitwise_and

Bitwise_not

Bitwise_or

Bitwise_xor

Blackman_window

Block_diag

Bmm

Broadcast_tensors

Bucketize

Can_cast

Cartesian_prod

Cat

Cdist

Ceil

Celu

Celu_

Chain_matmul

Channel_shuffle

Cholesky

Cholesky_inverse

Cholesky_solve

Chunk

Clamp

Clip

Clone

Combinations

Complex

Conj

Conv1d

Conv2d

Conv3d

Conv_tbc

Conv_transpose1d

Conv_transpose2d

Conv_transpose3d

Cos

Cosh

Cosine_similarity

Count_nonzero

Cross

Cummax

Cummin

Cumprod

Cumsum

Deg2rad

Dequantize

Det

Create a Device object

Diag

Diag_embed

Diagflat

Diagonal

Digamma

Dist

Div

Divide

Dot

Dstack

Torch data types

Eig

Einsum

Empty

Empty_like

Empty_strided

Eq

Equal

Erf

Erfc

Erfinv

Exp

Exp2

Expm1

Eye

Fft

Ifft

Irfft

Rfft

Floating point type info

Fix

Flatten

Flip

Fliplr

Flipud

Floor

Floor_divide

Fmod

Frac

Full

Full_like

Gather

Gcd

Ge

Create a Generator object

Geqrf

Ger

Greater

Greater_equal

Gt

Hamming_window

Hann_window

Heaviside

Histc

Hstack

Hypot

I0

Integer type info

Imag

Index_select

Inverse

Is_complex

Is_floating_point

Verifies if torch is installed

Is_nonzero

Isclose

Isfinite

Isinf

Isnan

Isneginf

Isposinf

Isreal

Istft

Kaiser_window

Kthvalue

Creates the corresponding layout

Lcm

Le

Lerp

Less

Less_equal

Lgamma

Linspace

Loads a saved object

Log

Log10

Log1p

Log2

Logaddexp

Logaddexp2

Logcumsumexp

Logdet

Logical_and

Logical_not

Logical_or

Logical_xor

Logit

Logspace

Logsumexp

Lstsq

Lt

LU

Lu_solve

Sets the seed for generating random numbers.

Masked_select

Matmul

Matrix_exp

Matrix_power

Matrix_rank

Max

Maximum

Mean

Median

Memory format

Meshgrid

Min

Minimum

Mm

Mode

Movedim

Mul

Multinomial

Multiply

Mv

Mvlgamma

Nanquantile

Nansum

Narrow

Ne

Neg

Negative

Nextafter

Nonzero

Norm

Normal

Not_equal

Ones

Ones_like

Orgqr

Ormqr

Outer

Pdist

Pinverse

Pixel_shuffle

Poisson

Polar

Polygamma

Pow

Prod

Promote_types

Qr

Creates the corresponding Scheme object

Quantile

Quantize_per_channel

Quantize_per_tensor

Rad2deg

Rand

Rand_like

Randint

Randint_like

Randn