# speechbrain.nnet.pooling module

Library implementing pooling.

Authors
• Titouan Parcollet 2020

• Mirco Ravanelli 2020

• Jianyuan Zhong 2020

## Summary

Classes:

 `AdaptivePool` This class implements the adaptive average pooling. `GaussianLowpassPooling` This class implements a learnable Gaussian lowpass pooling from `Pooling1d` This function implements 1d pooling of the input tensor. `Pooling2d` This function implements 2d pooling of the input tensor. `StatisticsPooling` This class implements a statistic pooling layer.

## Reference

class speechbrain.nnet.pooling.Pooling1d(pool_type, kernel_size, input_dims=3, pool_axis=1, ceil_mode=False, padding=0, dilation=1, stride=None)[source]

Bases: `Module`

This function implements 1d pooling of the input tensor.

Parameters
• pool_type (str) – It is the type of pooling function to use (‘avg’,’max’).

• kernel_size (int) – It is the kernel size that defines the pooling dimension. For instance, kernel size=3 applies a 1D Pooling with a size=3.

• input_dims (int) – The count of dimensions expected in the input.

• pool_axis (int) – The axis where the pooling is applied.

• stride (int) – It is the stride size.

• padding (int) – It is the number of padding elements to apply.

• dilation (int) – Controls the dilation factor of pooling.

• ceil_mode (int) – When True, will use ceil instead of floor to compute the output shape.

Example

```>>> pool = Pooling1d('max',3)
>>> inputs = torch.rand(10, 12, 40)
>>> output=pool(inputs)
>>> output.shape
torch.Size([10, 4, 40])
```
forward(x)[source]

Performs 1d pooling to the input tensor.

Parameters

x (torch.Tensor) – It represents a tensor for a mini-batch.

training: bool
class speechbrain.nnet.pooling.Pooling2d(pool_type, kernel_size, pool_axis=(1, 2), ceil_mode=False, padding=0, dilation=1, stride=None)[source]

Bases: `Module`

This function implements 2d pooling of the input tensor.

Parameters
• pool_type (str) – It is the type of pooling function to use (‘avg’,’max’).

• pool_axis (tuple) – It is a list containing the axis that will be considered during pooling.

• kernel_size (int) – It is the kernel size that defines the pooling dimension. For instance, kernel size=3,3 performs a 2D Pooling with a 3x3 kernel.

• stride (int) – It is the stride size.

• padding (int) – It is the number of padding elements to apply.

• dilation (int) – Controls the dilation factor of pooling.

• ceil_mode (int) – When True, will use ceil instead of floor to compute the output shape.

Example

```>>> pool = Pooling2d('max',(5,3))
>>> inputs = torch.rand(10, 15, 12)
>>> output=pool(inputs)
>>> output.shape
torch.Size([10, 3, 4])
```
forward(x)[source]

Performs 2d pooling to the input tensor.

Parameters

x (torch.Tensor) – It represents a tensor for a mini-batch.

training: bool
class speechbrain.nnet.pooling.StatisticsPooling(return_mean=True, return_std=True)[source]

Bases: `Module`

This class implements a statistic pooling layer.

It returns the mean and/or std of input tensor.

Parameters
• return_mean (True) – If True, the average pooling will be returned.

• return_std (True) – If True, the standard deviation will be returned.

Example

```>>> inp_tensor = torch.rand([5, 100, 50])
>>> sp_layer = StatisticsPooling()
>>> out_tensor = sp_layer(inp_tensor)
>>> out_tensor.shape
torch.Size([5, 1, 100])
```
forward(x, lengths=None)[source]

Calculates mean and std for a batch (input tensor).

Parameters

x (torch.Tensor) – It represents a tensor for a mini-batch.

training: bool

Bases: `Module`

This class implements the adaptive average pooling.

Parameters

delations (output_size) – The size of the output.

Example

```>>> pool = AdaptivePool(1)
>>> inp = torch.randn([8, 120, 40])
>>> output = pool(inp)
>>> output.shape
torch.Size([8, 1, 40])
```
forward(x)[source]

Performs adpative pooling to the input tensor.

Parameters

x (torch.Tensor) – It represents a tensor for a mini-batch.

training: bool

Bases: `Module`

This class implements a learnable Gaussian lowpass pooling from

Neil Zeghidour, Olivier Teboul, F{‘e}lix de Chaumont Quitry & Marco Tagliasacchi, “LEAF: A LEARNABLE FRONTEND FOR AUDIO CLASSIFICATION”, in Proc. of ICLR 2021 (https://arxiv.org/abs/2101.08596)

Parameters
• in_channels (int) – The number of input channels.

• kernel_size (int) – Kernel size of the gaussian lowpass filters.

• stride (int) – Stride factor of the convolutional filters. When the stride factor > 1, a decimation in time is performed.

• padding (str) – (same, valid). If “valid”, no padding is performed. If “same” and stride is 1, output shape is the same as the input shape.

• bias (bool) – If True, the additive bias b is adopted.

• skip_transpose (bool) – If False, uses batch x time x channel convention of speechbrain. If True, uses batch x channel x time convention.

Example

```>>> inp_tensor = torch.rand([10, 8000, 40])
>>> low_pass_pooling = GaussianLowpassPooling(
...     40, kernel_size=401, stride=160,
... )
>>> # parameters corresponding to a window of 25 ms and stride 10 ms at 16000 kHz
>>> out_tensor = low_pass_pooling(inp_tensor)
>>> out_tensor.shape
torch.Size([10, 50, 40])
```
training: bool
forward(x)[source]

Performs GaussianLowpass Pooling.

Parameters

x (torch.Tensor) – 3D tensor in input [batch,time,channels].