Pooling layers

Pooling layers

MaxPooling2D

Pooling using the max operation

class braid.berry.layers.MaxPooling2D(incoming, kernel_size, stride=1, pad='VALID', **kwargs)

Pooling using the max operation

This is used to subsample the output from convolutional layers. It works by convolving a kernel with a max operation across the activation of the previous layer. More specifically, it looks at a receptive field equal to [1, kernel_size, kernel_size, 1] and outputs the max value of the activations in this region, shifting then by stride amount and repeating.

incoming

: Layer or tf.Tensor

Parent layer, whose output is given as input to the current layer.

kernel_size

: int

The size of the kernel to consider for pooling.

stride

: int, optional (default = 1)

The amount of subsample.

pad

: string, optional (default = “VALID”)

Type of padding to apply to the input layer before doing pooling. Expected values - “VALID”, “SAME”. No padding is applied for “VALID”, while a padding of (kernel_size + 1) / 2 if “SAME”. This ensures that the output layer shape is the same as that of the input layer shape.

name

: string, optional (default = None)

Name of the layer. Should be specified for better readability ( inherited from Layer).

input_layer

: Layer or tf.Tensor

Input layer to this layer.

input_shape

: tuple

Shape of the incoming layer.

output

: tf.Tensor

The Tensor obtained after performing the transformation applied by this layer.

output_shape

: tuple

Shape of the output tensor.

type

: string

Return the name of the class.

See also

Inherits class Layer.

get_output_for()

Perform the max pooling operation and return the output tf.Tensor.

tf.Tensor

Output tensor of this layer.

get_output_shape_for(input_shape)

Shape of the output tensor after performing MaxPooling.

input_shape

: tuple or list

Shape of the input layer.

tuple

Shape of the output tensor.

Note

Each dimension of the output is given as

\[l_o = \frac{( W - F +2P)}{S} + 1\]

where \(W\) is the width of the input layer dim, \(F\) is the kernel_size, \(P\) is the amount of padding applied and \(S\) is the stride.

validate_input_layer(incoming)

Validate the input layer dimensions.

Valid input layer would be 4D.

incoming

: Layer or tf.Tensor

Parent layer, whose output is given as input to the current layer.

bool

True if connection is valid or raises an exceptions.AssertionError.