# tensorplay.nn.functional

Source: https://www.tensorplay.cn/docs/nn.functional.html

# tensorplay.nn.functional

## Convolution functions

[tensorplay.nn.functional.conv1d](generated/tensorplay.nn.functional.conv1d.html#tensorplay.nn.functional.conv1d)

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

[tensorplay.nn.functional.conv2d](generated/tensorplay.nn.functional.conv2d.html#tensorplay.nn.functional.conv2d)

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

[tensorplay.nn.functional.conv3d](generated/tensorplay.nn.functional.conv3d.html#tensorplay.nn.functional.conv3d)

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

[tensorplay.nn.functional.conv_transpose1d](generated/tensorplay.nn.functional.conv_transpose1d.html#tensorplay.nn.functional.conv_transpose1d)

[tensorplay.nn.functional.conv_transpose2d](generated/tensorplay.nn.functional.conv_transpose2d.html#tensorplay.nn.functional.conv_transpose2d)

[tensorplay.nn.functional.conv_transpose3d](generated/tensorplay.nn.functional.conv_transpose3d.html#tensorplay.nn.functional.conv_transpose3d)

[tensorplay.nn.functional.unfold](generated/tensorplay.nn.functional.unfold.html#tensorplay.nn.functional.unfold)

Extract sliding local blocks from a batched input tensor (torch F.unfold, i.e. aten::im2col).

[tensorplay.nn.functional.fold](generated/tensorplay.nn.functional.fold.html#tensorplay.nn.functional.fold)

Combine an array of sliding local blocks into a tensor containing them all (torch F.fold, i.e. aten::col2im).

## Pooling functions

[tensorplay.nn.functional.avg_pool1d](generated/tensorplay.nn.functional.avg_pool1d.html#tensorplay.nn.functional.avg_pool1d)

avg_pool1d(input, kernel_size, stride=None, padding=0, ceil_mode=False, count_include_pad=True, divisor_override=None) -> Tensor

[tensorplay.nn.functional.avg_pool2d](generated/tensorplay.nn.functional.avg_pool2d.html#tensorplay.nn.functional.avg_pool2d)

[tensorplay.nn.functional.avg_pool3d](generated/tensorplay.nn.functional.avg_pool3d.html#tensorplay.nn.functional.avg_pool3d)

avg_pool3d(input, kernel_size, stride=None, padding=0, ceil_mode=False, count_include_pad=True, divisor_override=None) -> Tensor

[tensorplay.nn.functional.max_pool1d](generated/tensorplay.nn.functional.max_pool1d.html#tensorplay.nn.functional.max_pool1d)

max_pool1d(input, kernel_size, stride=None, padding=0, dilation=1, ceil_mode=False, return_indices=False) -> Tensor

[tensorplay.nn.functional.max_pool2d](generated/tensorplay.nn.functional.max_pool2d.html#tensorplay.nn.functional.max_pool2d)

[tensorplay.nn.functional.max_pool3d](generated/tensorplay.nn.functional.max_pool3d.html#tensorplay.nn.functional.max_pool3d)

max_pool3d(input, kernel_size, stride=None, padding=0, dilation=1, ceil_mode=False, return_indices=False) -> Tensor

[tensorplay.nn.functional.max_unpool1d](generated/tensorplay.nn.functional.max_unpool1d.html#tensorplay.nn.functional.max_unpool1d)

Compute a partial inverse of MaxPool1d.

[tensorplay.nn.functional.max_unpool2d](generated/tensorplay.nn.functional.max_unpool2d.html#tensorplay.nn.functional.max_unpool2d)

Compute a partial inverse of MaxPool2d.

[tensorplay.nn.functional.max_unpool3d](generated/tensorplay.nn.functional.max_unpool3d.html#tensorplay.nn.functional.max_unpool3d)

Compute a partial inverse of MaxPool3d.

[tensorplay.nn.functional.lp_pool1d](generated/tensorplay.nn.functional.lp_pool1d.html#tensorplay.nn.functional.lp_pool1d)

Apply a 1D power-average pooling over an input signal.

[tensorplay.nn.functional.lp_pool2d](generated/tensorplay.nn.functional.lp_pool2d.html#tensorplay.nn.functional.lp_pool2d)

Apply a 2D power-average pooling over an input signal.

[tensorplay.nn.functional.lp_pool3d](generated/tensorplay.nn.functional.lp_pool3d.html#tensorplay.nn.functional.lp_pool3d)

Apply a 3D power-average pooling over an input signal.

[tensorplay.nn.functional.adaptive_max_pool1d](generated/tensorplay.nn.functional.adaptive_max_pool1d.html#tensorplay.nn.functional.adaptive_max_pool1d)

[tensorplay.nn.functional.adaptive_max_pool2d](generated/tensorplay.nn.functional.adaptive_max_pool2d.html#tensorplay.nn.functional.adaptive_max_pool2d)

[tensorplay.nn.functional.adaptive_avg_pool1d](generated/tensorplay.nn.functional.adaptive_avg_pool1d.html#tensorplay.nn.functional.adaptive_avg_pool1d)

[tensorplay.nn.functional.adaptive_avg_pool2d](generated/tensorplay.nn.functional.adaptive_avg_pool2d.html#tensorplay.nn.functional.adaptive_avg_pool2d)

[tensorplay.nn.functional.adaptive_avg_pool3d](generated/tensorplay.nn.functional.adaptive_avg_pool3d.html#tensorplay.nn.functional.adaptive_avg_pool3d)

Apply a 3D adaptive average pooling over an input signal.

[tensorplay.nn.functional.fractional_max_pool2d](generated/tensorplay.nn.functional.fractional_max_pool2d.html#tensorplay.nn.functional.fractional_max_pool2d)

Applies 2D fractional max pooling over an input signal.

[tensorplay.nn.functional.fractional_max_pool3d](generated/tensorplay.nn.functional.fractional_max_pool3d.html#tensorplay.nn.functional.fractional_max_pool3d)

Applies 3D fractional max pooling over an input signal.

## Attention Mechanisms

[tensorplay.nn.functional.scaled_dot_product_attention](generated/tensorplay.nn.functional.scaled_dot_product_attention.html#tensorplay.nn.functional.scaled_dot_product_attention)

scaled_dot_product_attention(query, key, value, attn_mask=None, dropout_p=0.0, is_causal=False, scale=None, backend=None) -> Tensor

## Non-linear activation functions

[tensorplay.nn.functional.threshold](generated/tensorplay.nn.functional.threshold.html#tensorplay.nn.functional.threshold)

Apply a threshold to each element of the input Tensor.

[tensorplay.nn.functional.relu](generated/tensorplay.nn.functional.relu.html#tensorplay.nn.functional.relu)

[tensorplay.nn.functional.hardtanh](generated/tensorplay.nn.functional.hardtanh.html#tensorplay.nn.functional.hardtanh)

[tensorplay.nn.functional.hardswish](generated/tensorplay.nn.functional.hardswish.html#tensorplay.nn.functional.hardswish)

[tensorplay.nn.functional.relu6](generated/tensorplay.nn.functional.relu6.html#tensorplay.nn.functional.relu6)

ReLU6: \(\min(\max(0, x), 6)\) — torch.nn.functional.relu6.

[tensorplay.nn.functional.elu](generated/tensorplay.nn.functional.elu.html#tensorplay.nn.functional.elu)

[tensorplay.nn.functional.selu](generated/tensorplay.nn.functional.selu.html#tensorplay.nn.functional.selu)

[tensorplay.nn.functional.celu](generated/tensorplay.nn.functional.celu.html#tensorplay.nn.functional.celu)

[tensorplay.nn.functional.leaky_relu](generated/tensorplay.nn.functional.leaky_relu.html#tensorplay.nn.functional.leaky_relu)

[tensorplay.nn.functional.prelu](generated/tensorplay.nn.functional.prelu.html#tensorplay.nn.functional.prelu)

[tensorplay.nn.functional.rrelu](generated/tensorplay.nn.functional.rrelu.html#tensorplay.nn.functional.rrelu)

Randomized leaky ReLU.

[tensorplay.nn.functional.glu](generated/tensorplay.nn.functional.glu.html#tensorplay.nn.functional.glu)

Gated Linear Unit: \(a * \sigma(b)\) where the input is split in half along dim.

[tensorplay.nn.functional.gelu](generated/tensorplay.nn.functional.gelu.html#tensorplay.nn.functional.gelu)

When approximate is 'none', applies \(\text{GELU}(x) = x * \Phi(x)\); 'tanh' uses the tanh estimation.

[tensorplay.nn.functional.logsigmoid](generated/tensorplay.nn.functional.logsigmoid.html#tensorplay.nn.functional.logsigmoid)

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

[tensorplay.nn.functional.hardshrink](generated/tensorplay.nn.functional.hardshrink.html#tensorplay.nn.functional.hardshrink)

Applies the hard shrinkage function element-wise.

[tensorplay.nn.functional.tanhshrink](generated/tensorplay.nn.functional.tanhshrink.html#tensorplay.nn.functional.tanhshrink)

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

[tensorplay.nn.functional.softsign](generated/tensorplay.nn.functional.softsign.html#tensorplay.nn.functional.softsign)

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

[tensorplay.nn.functional.softplus](generated/tensorplay.nn.functional.softplus.html#tensorplay.nn.functional.softplus)

[tensorplay.nn.functional.softmin](generated/tensorplay.nn.functional.softmin.html#tensorplay.nn.functional.softmin)

Apply a softmin function.

[tensorplay.nn.functional.softmax](generated/tensorplay.nn.functional.softmax.html#tensorplay.nn.functional.softmax)

[tensorplay.nn.functional.softshrink](generated/tensorplay.nn.functional.softshrink.html#tensorplay.nn.functional.softshrink)

Applies the soft shrinkage function element-wise.

[tensorplay.nn.functional.gumbel_softmax](generated/tensorplay.nn.functional.gumbel_softmax.html#tensorplay.nn.functional.gumbel_softmax)

Sample from the Gumbel-Softmax distribution and optionally discretize.

[tensorplay.nn.functional.log_softmax](generated/tensorplay.nn.functional.log_softmax.html#tensorplay.nn.functional.log_softmax)

[tensorplay.nn.functional.tanh](generated/tensorplay.nn.functional.tanh.html#tensorplay.nn.functional.tanh)

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

[tensorplay.nn.functional.sigmoid](generated/tensorplay.nn.functional.sigmoid.html#tensorplay.nn.functional.sigmoid)

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

[tensorplay.nn.functional.hardsigmoid](generated/tensorplay.nn.functional.hardsigmoid.html#tensorplay.nn.functional.hardsigmoid)

[tensorplay.nn.functional.silu](generated/tensorplay.nn.functional.silu.html#tensorplay.nn.functional.silu)

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

[tensorplay.nn.functional.mish](generated/tensorplay.nn.functional.mish.html#tensorplay.nn.functional.mish)

[tensorplay.nn.functional.batch_norm](generated/tensorplay.nn.functional.batch_norm.html#tensorplay.nn.functional.batch_norm)

[tensorplay.nn.functional.group_norm](generated/tensorplay.nn.functional.group_norm.html#tensorplay.nn.functional.group_norm)

[tensorplay.nn.functional.instance_norm](generated/tensorplay.nn.functional.instance_norm.html#tensorplay.nn.functional.instance_norm)

[tensorplay.nn.functional.layer_norm](generated/tensorplay.nn.functional.layer_norm.html#tensorplay.nn.functional.layer_norm)

[tensorplay.nn.functional.local_response_norm](generated/tensorplay.nn.functional.local_response_norm.html#tensorplay.nn.functional.local_response_norm)

Apply local response normalization over an input signal.

[tensorplay.nn.functional.rms_norm](generated/tensorplay.nn.functional.rms_norm.html#tensorplay.nn.functional.rms_norm)

Apply Root Mean Square Layer Normalization — composed per the ATen rms_norm composite (fp32 compute for reduced dtypes).

[tensorplay.nn.functional.normalize](generated/tensorplay.nn.functional.normalize.html#tensorplay.nn.functional.normalize)

Performs \(L_p\) normalization over the specified dimension — torch.nn.functional.normalize divides by clamp_min(norm, eps).

## Linear functions

[tensorplay.nn.functional.linear](generated/tensorplay.nn.functional.linear.html#tensorplay.nn.functional.linear)

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

[tensorplay.nn.functional.bilinear](generated/tensorplay.nn.functional.bilinear.html#tensorplay.nn.functional.bilinear)

## Dropout functions

[tensorplay.nn.functional.dropout](generated/tensorplay.nn.functional.dropout.html#tensorplay.nn.functional.dropout)

[tensorplay.nn.functional.alpha_dropout](generated/tensorplay.nn.functional.alpha_dropout.html#tensorplay.nn.functional.alpha_dropout)

[tensorplay.nn.functional.feature_alpha_dropout](generated/tensorplay.nn.functional.feature_alpha_dropout.html#tensorplay.nn.functional.feature_alpha_dropout)

Randomly masks out entire channels, setting activations to the negative saturation value of the SELU activation function.

[tensorplay.nn.functional.dropout1d](generated/tensorplay.nn.functional.dropout1d.html#tensorplay.nn.functional.dropout1d)

Randomly zero out entire channels (a channel is a 1D feature map).

[tensorplay.nn.functional.dropout2d](generated/tensorplay.nn.functional.dropout2d.html#tensorplay.nn.functional.dropout2d)

[tensorplay.nn.functional.dropout3d](generated/tensorplay.nn.functional.dropout3d.html#tensorplay.nn.functional.dropout3d)

## Sparse functions

[tensorplay.nn.functional.embedding](generated/tensorplay.nn.functional.embedding.html#tensorplay.nn.functional.embedding)

[tensorplay.nn.functional.embedding_bag](generated/tensorplay.nn.functional.embedding_bag.html#tensorplay.nn.functional.embedding_bag)

Compute sums, means or maxes of bags of embeddings.

[tensorplay.nn.functional.one_hot](generated/tensorplay.nn.functional.one_hot.html#tensorplay.nn.functional.one_hot)

Returns long tensor shaped tensor.shape + (num_classes,) with a 1 at each label position — port of ATen one_hot.

## Distance functions

[tensorplay.nn.functional.pairwise_distance](generated/tensorplay.nn.functional.pairwise_distance.html#tensorplay.nn.functional.pairwise_distance)

Computes the pairwise distance between input vectors.

[tensorplay.nn.functional.cosine_similarity](generated/tensorplay.nn.functional.cosine_similarity.html#tensorplay.nn.functional.cosine_similarity)

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

[tensorplay.nn.functional.pdist](generated/tensorplay.nn.functional.pdist.html#tensorplay.nn.functional.pdist)

Computes the pairwise distance between rows of input.

## Loss functions

[tensorplay.nn.functional.binary_cross_entropy](generated/tensorplay.nn.functional.binary_cross_entropy.html#tensorplay.nn.functional.binary_cross_entropy)

Compute Binary Cross Entropy between the target and input probabilities.

[tensorplay.nn.functional.binary_cross_entropy_with_logits](generated/tensorplay.nn.functional.binary_cross_entropy_with_logits.html#tensorplay.nn.functional.binary_cross_entropy_with_logits)

Compute Binary Cross Entropy between target and input logits.

[tensorplay.nn.functional.poisson_nll_loss](generated/tensorplay.nn.functional.poisson_nll_loss.html#tensorplay.nn.functional.poisson_nll_loss)

Compute the Poisson negative log likelihood loss.

[tensorplay.nn.functional.cosine_embedding_loss](generated/tensorplay.nn.functional.cosine_embedding_loss.html#tensorplay.nn.functional.cosine_embedding_loss)

Compute the cosine embedding loss.

[tensorplay.nn.functional.cross_entropy](generated/tensorplay.nn.functional.cross_entropy.html#tensorplay.nn.functional.cross_entropy)

Compute the cross entropy loss between input logits and target.

[tensorplay.nn.functional.ctc_loss](generated/tensorplay.nn.functional.ctc_loss.html#tensorplay.nn.functional.ctc_loss)

Compute the Connectionist Temporal Classification loss.

[tensorplay.nn.functional.gaussian_nll_loss](generated/tensorplay.nn.functional.gaussian_nll_loss.html#tensorplay.nn.functional.gaussian_nll_loss)

Compute the Gaussian negative log likelihood loss.

[tensorplay.nn.functional.hinge_embedding_loss](generated/tensorplay.nn.functional.hinge_embedding_loss.html#tensorplay.nn.functional.hinge_embedding_loss)

Compute the hinge embedding loss.

[tensorplay.nn.functional.kl_div](generated/tensorplay.nn.functional.kl_div.html#tensorplay.nn.functional.kl_div)

Compute the KL Divergence loss.

[tensorplay.nn.functional.l1_loss](generated/tensorplay.nn.functional.l1_loss.html#tensorplay.nn.functional.l1_loss)

Compute the L1 loss, with optional weighting.

[tensorplay.nn.functional.linear_cross_entropy](generated/tensorplay.nn.functional.linear_cross_entropy.html#tensorplay.nn.functional.linear_cross_entropy)

Compute cross entropy between input, transformed linearly, and target.

[tensorplay.nn.functional.mse_loss](generated/tensorplay.nn.functional.mse_loss.html#tensorplay.nn.functional.mse_loss)

[tensorplay.nn.functional.margin_ranking_loss](generated/tensorplay.nn.functional.margin_ranking_loss.html#tensorplay.nn.functional.margin_ranking_loss)

Compute the margin ranking loss.

[tensorplay.nn.functional.multilabel_margin_loss](generated/tensorplay.nn.functional.multilabel_margin_loss.html#tensorplay.nn.functional.multilabel_margin_loss)

Compute the multilabel margin loss.

[tensorplay.nn.functional.multilabel_soft_margin_loss](generated/tensorplay.nn.functional.multilabel_soft_margin_loss.html#tensorplay.nn.functional.multilabel_soft_margin_loss)

Compute the multilabel soft margin loss.

[tensorplay.nn.functional.multi_margin_loss](generated/tensorplay.nn.functional.multi_margin_loss.html#tensorplay.nn.functional.multi_margin_loss)

Compute the multi margin loss, with optional weighting.

[tensorplay.nn.functional.nll_loss](generated/tensorplay.nn.functional.nll_loss.html#tensorplay.nn.functional.nll_loss)

The negative log likelihood loss.

[tensorplay.nn.functional.huber_loss](generated/tensorplay.nn.functional.huber_loss.html#tensorplay.nn.functional.huber_loss)

Compute the Huber loss, with optional weighting.

[tensorplay.nn.functional.smooth_l1_loss](generated/tensorplay.nn.functional.smooth_l1_loss.html#tensorplay.nn.functional.smooth_l1_loss)

Compute the Smooth L1 loss.

[tensorplay.nn.functional.soft_margin_loss](generated/tensorplay.nn.functional.soft_margin_loss.html#tensorplay.nn.functional.soft_margin_loss)

Compute the soft margin loss.

[tensorplay.nn.functional.triplet_margin_loss](generated/tensorplay.nn.functional.triplet_margin_loss.html#tensorplay.nn.functional.triplet_margin_loss)

Compute the triplet loss between given input tensors and a margin greater than 0.

[tensorplay.nn.functional.triplet_margin_with_distance_loss](generated/tensorplay.nn.functional.triplet_margin_with_distance_loss.html#tensorplay.nn.functional.triplet_margin_with_distance_loss)

Compute the triplet margin loss using a custom distance function.

## Vision functions

[tensorplay.nn.functional.pixel_shuffle](generated/tensorplay.nn.functional.pixel_shuffle.html#tensorplay.nn.functional.pixel_shuffle)

Rearranges elements in a tensor of shape (*, C x r^2, H, W) to a tensor of shape (*, C, H x r, W x r).

[tensorplay.nn.functional.pixel_unshuffle](generated/tensorplay.nn.functional.pixel_unshuffle.html#tensorplay.nn.functional.pixel_unshuffle)

Reverses the pixel_shuffle() transformation: (*, C, H x r, W x r) -> (*, C x r^2, H, W).

[tensorplay.nn.functional.pad](generated/tensorplay.nn.functional.pad.html#tensorplay.nn.functional.pad)

Pads tensor.

[tensorplay.nn.functional.interpolate](generated/tensorplay.nn.functional.interpolate.html#tensorplay.nn.functional.interpolate)

interpolate(input, size=None, scale_factor=None, mode='nearest', align_corners=None) -> Tensor

[tensorplay.nn.functional.upsample](generated/tensorplay.nn.functional.upsample.html#tensorplay.nn.functional.upsample)

Upsamples the input to the given size or scale_factor.

[tensorplay.nn.functional.upsample_nearest](generated/tensorplay.nn.functional.upsample_nearest.html#tensorplay.nn.functional.upsample_nearest)

Upsamples the input using nearest neighbours.

[tensorplay.nn.functional.upsample_bilinear](generated/tensorplay.nn.functional.upsample_bilinear.html#tensorplay.nn.functional.upsample_bilinear)

Upsamples the input using bilinear upsampling.

[tensorplay.nn.functional.grid_sample](generated/tensorplay.nn.functional.grid_sample.html#tensorplay.nn.functional.grid_sample)

Compute grid sample.

[tensorplay.nn.functional.affine_grid](generated/tensorplay.nn.functional.affine_grid.html#tensorplay.nn.functional.affine_grid)

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

### data_parallel

## Low-Precision functions

[tensorplay.nn.functional.grouped_mm](generated/tensorplay.nn.functional.grouped_mm.html#tensorplay.nn.functional.grouped_mm)

[tensorplay.nn.functional.scaled_mm](generated/tensorplay.nn.functional.scaled_mm.html#tensorplay.nn.functional.scaled_mm)

[tensorplay.nn.functional.scaled_grouped_mm](generated/tensorplay.nn.functional.scaled_grouped_mm.html#tensorplay.nn.functional.scaled_grouped_mm)

## TensorPlay-specific additions

[DType](generated/tensorplay.nn.functional.DType.html#tensorplay.nn.functional.DType)

Members:

[Tensor](generated/tensorplay.nn.functional.Tensor.html#tensorplay.nn.functional.Tensor)

alias of TensorBase

[adaptive_max_pool1d_with_indices](generated/tensorplay.nn.functional.adaptive_max_pool1d_with_indices.html#tensorplay.nn.functional.adaptive_max_pool1d_with_indices)

Applies a 1D adaptive max pooling over an input signal, returning (output, indices).

[adaptive_max_pool2d_with_indices](generated/tensorplay.nn.functional.adaptive_max_pool2d_with_indices.html#tensorplay.nn.functional.adaptive_max_pool2d_with_indices)

Applies a 2D adaptive max pooling over an input signal composed of several input planes, returning (output, indices).

[adaptive_max_pool3d_with_indices](generated/tensorplay.nn.functional.adaptive_max_pool3d_with_indices.html#tensorplay.nn.functional.adaptive_max_pool3d_with_indices)

Applies a 3D adaptive max pooling over an input signal, returning (output, indices).

[channel_shuffle](generated/tensorplay.nn.functional.channel_shuffle.html#tensorplay.nn.functional.channel_shuffle)

Divide the channels in a tensor into g groups and rearrange them as in ShuffleNet: (*, C, H, W) -> (*, C, H, W) with channels interleaved across groups.

[conv_tbc](generated/tensorplay.nn.functional.conv_tbc.html#tensorplay.nn.functional.conv_tbc)

Applies a 1D convolution over an input of shape (T, B, C) along the time dimension (torch.conv_tbc).

[flatten](generated/tensorplay.nn.functional.flatten.html#tensorplay.nn.functional.flatten)

[fractional_max_pool2d_with_indices](generated/tensorplay.nn.functional.fractional_max_pool2d_with_indices.html#tensorplay.nn.functional.fractional_max_pool2d_with_indices)

Applies 2D fractional max pooling over an input signal composed of several input planes, returning (output, indices).

[fractional_max_pool3d_with_indices](generated/tensorplay.nn.functional.fractional_max_pool3d_with_indices.html#tensorplay.nn.functional.fractional_max_pool3d_with_indices)

Applies 3D fractional max pooling over an input signal composed of several input planes, returning (output, indices).

[max_pool1d_with_indices](generated/tensorplay.nn.functional.max_pool1d_with_indices.html#tensorplay.nn.functional.max_pool1d_with_indices)

Applies a 1D max pooling over an input signal, returning (output, indices).

[max_pool2d_with_indices](generated/tensorplay.nn.functional.max_pool2d_with_indices.html#tensorplay.nn.functional.max_pool2d_with_indices)

Applies a 2D max pooling over an input composed of several input planes, returning (output, indices).

[max_pool3d_with_indices](generated/tensorplay.nn.functional.max_pool3d_with_indices.html#tensorplay.nn.functional.max_pool3d_with_indices)

Applies a 3D max pooling over an input signal, returning (output, indices).

[multi_head_attention_forward](generated/tensorplay.nn.functional.multi_head_attention_forward.html#tensorplay.nn.functional.multi_head_attention_forward)

torch-compatible multi_head_attention_forward.

[native_channel_shuffle](generated/tensorplay.nn.functional.native_channel_shuffle.html#tensorplay.nn.functional.native_channel_shuffle)

Native channel shuffle primitive (torch.native_channel_shuffle).