Beginning Anomaly Detection Using

pool_size: An integer value. If an integer n is given, then the 

window size of the pooling layer is 

1xn. These are also the factors to 

downscale by, so if an integer 

n is passed in, the dimensions for both 

height and width are downscaled by that factor.

• 

strides: An integer or None. By default, the stride is set to pool_size. 

If you pass in an integer, the pooling window moves by integer 

n 

amount after completing its pooling operation on a set of entries.

• 

padding: ‘valid’ or ‘same’. ‘valid’ means there’s no zero padding, and 

‘same’ pads the output sequence with zeroes so that it matches the 

dimensions of the input sequence.

• 

data_format: ‘channels_first’ or ‘channels_last’. This tells the 

flattening layer how to format the flattened output to preserve the 

formatting of channels first or channels last. ‘channels_first’ has 

the format (batch, features, steps), and ‘channels_last’ has the 

format (batch, steps, features).

 MaxPooling2D

keras.layers.MaxPooling2D()

It applies max pooling on a 2D input. To get a better idea of how max pooling works, 

check out Chapter 

3

.

Appendix A   intro to KerAs

---

340

This is the list of parameters:

• 

pool_size: An integer that dictates the size of the pooling window. 

An integer of