Beginning Anomaly Detection Using

n makes the pooling window size n, meaning it sifts 

through 

n entries at a time and selects the maximum value to pass on 

to the output.

• 

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. It is 

also a factor that determines how much to downscale the dimensions 

by, as a parameter 

n will reduce the dimensions by a factor n.

• 

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.