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

Applies a 2D convolution over an input image composed of several input planes.

Applies a 3D convolution over an input image composed of several input planes.

Applies a 1D transposed convolution operator over an input signal composed of several input planes, sometimes also called "deconvolution".

Applies a 2D transposed convolution operator over an input image composed of several input planes, sometimes also called "deconvolution".

Applies a 3D transposed convolution operator over an input image composed of several input planes, sometimes also called "deconvolution"

Extracts sliding local blocks from a batched input tensor.

Combines an array of sliding local blocks into a large containing tensor.

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

Applies 2D average-pooling operation in $kH \times kW$ regions by step size $sH \times sW$ steps.

Applies 3D average-pooling operation in $kT \times kH \times kW$ regions by step size $sT \times sH \times sW$ steps.

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

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

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.

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 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 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.

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

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

Computes scaled dot product attention on query, key and value tensors, using an optional attention mask if passed, and applying dropout if a probability greater than 0.0 is specified.

Thresholds each element of the input Tensor.

In-place version of threshold().

Applies the rectified linear unit function element-wise.

In-place version of relu().

Applies the HardTanh function element-wise.

In-place version of hardtanh().

Applies the hardswish function, element-wise, as described in the paper:

Applies the element-wise function $\text{ReLU6}(x) = \min(\max(0,x), 6)$.

Applies the Exponential Linear Unit (ELU) function element-wise.

In-place version of elu().

Applies element-wise, $\text{SELU}(x) = scale * (\max(0,x) + \min(0, \alpha * (\exp(x) - 1)))$, with $\alpha=1.6732632423543772848170429916717$ and $scale=1.0507009873554804934193349852946$.

Applies element-wise, $\text{CELU}(x) = \max(0,x) + \min(0, \alpha * (\exp(x/\alpha) - 1))$.

Applies element-wise, $\text{LeakyReLU}(x) = \max(0, x) + \text{negative\_slope} * \min(0, x)$

In-place version of leaky_relu().

Applies element-wise the function $\text{PReLU}(x) = \max(0,x) + \text{weight} * \min(0,x)$ where weight is a learnable parameter.

Randomized leaky ReLU.

In-place version of rrelu().

The gated linear unit.

When the approximate argument is 'none', it applies element-wise the function $\text{GELU}(x) = x * \Phi(x)$

Applies element-wise $\text{LogSigmoid}(x_i) = \log \left(\frac{1}{1 + \exp(-x_i)}\right)$

Applies the hard shrinkage function element-wise

Applies element-wise, $\text{Tanhshrink}(x) = x - \text{Tanh}(x)$

Applies element-wise, the function $\text{SoftSign}(x) = \frac{x}{1 + |x|}$

Applies element-wise, the function $\text{Softplus}(x) = \frac{1}{\beta} * \log(1 + \exp(\beta * x))$.

Applies a softmin function.

Applies a softmax function.

Applies the soft shrinkage function elementwise

Samples from the Gumbel-Softmax distribution (Link 1 Link 2) and optionally discretizes.

Applies a softmax followed by a logarithm.

Applies element-wise, $\text{Tanh}(x) = \tanh(x) = \frac{\exp(x) - \exp(-x)}{\exp(x) + \exp(-x)}$

Applies the element-wise function $\text{Sigmoid}(x) = \frac{1}{1 + \exp(-x)}$

Applies the element-wise function

Applies the Sigmoid Linear Unit (SiLU) function, element-wise.

Applies the Mish function, element-wise.

Applies Batch Normalization for each channel across a batch of data.

Applies Group Normalization for last certain number of dimensions.

Applies Instance Normalization for each channel in each data sample in a batch.

Applies Layer Normalization for last certain number of dimensions.

Applies local response normalization over an input signal composed of several input planes, where channels occupy the second dimension.

Performs $L_p$ normalization of inputs over specified dimension.

Applies a linear transformation to the incoming data: $y = xA^T + b$.

Applies a bilinear transformation to the incoming data: $y = x_1^T A x_2 + b$

During training, randomly zeroes some of the elements of the input tensor with probability p using samples from a Bernoulli distribution.

Applies alpha dropout to the input.

Randomly masks out entire channels (a channel is a feature map, e.g.

Randomly zero out entire channels (a channel is a 1D feature map, e.g., the $j$-th channel of the $i$-th sample in the batched input is a 1D tensor $\text{input}[i, j]$) of the input tensor).

Randomly zero out entire channels (a channel is a 2D feature map, e.g., the $j$-th channel of the $i$-th sample in the batched input is a 2D tensor $\text{input}[i, j]$) of the input tensor).

Randomly zero out entire channels (a channel is a 3D feature map, e.g., the $j$-th channel of the $i$-th sample in the batched input is a 3D tensor $\text{input}[i, j]$) of the input tensor).

A simple lookup table that looks up embeddings in a fixed dictionary and size.

Computes sums, means or maxes of bags of embeddings, without instantiating the intermediate embeddings.

Takes LongTensor with index values of shape (*) and returns a tensor of shape (*, num_classes) that have zeros everywhere except where the index of last dimension matches the corresponding value of the input tensor, in which case it will be 1.

See torch.nn.PairwiseDistance for details

Returns cosine similarity between x1 and x2, computed along dim.

Computes the p-norm distance between every pair of row vectors in the input.

Function that measures the Binary Cross Entropy between the target and input probabilities.

Function that measures Binary Cross Entropy between target and input logits.

Poisson negative log likelihood loss.

See CosineEmbeddingLoss for details.

This criterion computes the cross entropy loss between input logits and target.

The Connectionist Temporal Classification loss.

Gaussian negative log likelihood loss.

See HingeEmbeddingLoss for details.

The Kullback-Leibler divergence Loss

Function that takes the mean element-wise absolute value difference.

Measures the element-wise mean squared error.

See MarginRankingLoss for details.

See MultiLabelMarginLoss for details.

See MultiLabelSoftMarginLoss for details.

See MultiMarginLoss for details.

The negative log likelihood loss.

Function that uses a squared term if the absolute element-wise error falls below delta and a delta-scaled L1 term otherwise.

Function that uses a squared term if the absolute element-wise error falls below beta and an L1 term otherwise.

See SoftMarginLoss for details.

See TripletMarginLoss for details

See TripletMarginWithDistanceLoss for details.

Rearranges elements in a tensor of shape $(*, C \times r^2, H, W)$ to a tensor of shape $(*, C, H \times r, W \times r)$, where r is the upscale_factor.

Reverses the PixelShuffle operation by rearranging elements in a tensor of shape $(*, C, H \times r, W \times r)$ to a tensor of shape $(*, C \times r^2, H, W)$, where r is the downscale_factor.

Pads tensor.

Down/up samples the input to either the given size or the given scale_factor

Upsamples the input to either the given size or the given scale_factor

Upsamples the input, using nearest neighbours' pixel values.

Upsamples the input, using bilinear upsampling.

Given an input and a flow-field grid, computes the output using input values and pixel locations from grid.

Generates a 2D or 3D flow field (sampling grid), given a batch of affine matrices theta.

torch.nn.parallel.data_parallel

Evaluates module(input) in parallel across the GPUs given in device_ids.