MaxPool2D

class MaxPool2D(kernel_size: int, stride: int = None)

Bases: bluebird.layers.layer.Layer

Applies a 2D max pooling.

Example:

conv = MaxPool2D(kernel_size=5)
net = NeuralNet([
        ...
        conv,
        ...
    ])

__init__(kernel_size: int, stride: int = None)

Initalize the object.

Parameters

• kernel_size (int) – size of the window

• stride (int) – defines how much the window moves, defaults to kernel_size

Methods

__init__(kernel_size[, stride])	Initalize the object.
backward(grad)	Used to calculate the gradients of weights and biases.
build(input_size)	Used to finalize building layers.
create_mask(a)	Creates the one hot max mask.
forward(inputs[, training])	Called each time the data passes throughout the nework.
get_params()	Returns params of layer.

backward(grad: numpy.ndarray) → numpy.ndarray

Used to calculate the gradients of weights and biases.

Parameters

grad (Tensor) – gradient from previous layer or loss function.

Returns

Gradient

Return type

Tensor

build(input_size) → None

Used to finalize building layers.

Important to note, you should set the input_size for the layer in here. Does not apply to the activation functions, you don’t need implement it in them.

Parameters

input_size (int) – output size from previous layer

Raises

NotImplementedError –

create_mask(a: numpy.ndarray) → numpy.ndarray

Creates the one hot max mask.

Parameters

a (Tensor) – tensor you wish to create the mask from

Returns

mask

Return type

Tensor

forward(inputs: numpy.ndarray, training: bool = False) → numpy.ndarray

Called each time the data passes throughout the nework.

Parameters

• inputs (Tensor) – output from the previous layer

• training (bool, optional) – set to true during training, and is false when network predicts

Returns

processed input data

Return type

Tensor

get_params() → Dict

Returns params of layer.

Returns

all params of layer

Return type

dict