Beginning Anomaly Detection Using

n means a dilation factor of n. A tuple of two integers 

allows you to specify (

vertical_dilation, horizontal_dilation). 

Default = 1.

• 

groups: Controls the connections between the input and output 

nodes. Groups=1 means all inputs correlate with all outputs. 

Groups=2 means there’s really two convolutional layers side by side, 

so half the inputs go to half the outputs. Default = 1.

• 

bias: Whether or not to use bias. Default = True.

appendix B   intro to pytorch

---

380

 Linear

torch.nn.Linear()

This is a neural network layer comprised of densely-connected neurons. Basically, 

every node in this layer is fully connected with the previous and next layers if there are any.

Here are the parameters:

• 

in_features: The size of each input sample; number of inputs.

• 

out_features: The size of each output sample; number of outputs.

• 

bias: Whether or not to use bias. Default = True.

 MaxPooling1D

torch.nn.MaxPool1d()

This applies max pooling on a 1D input. To get a better idea of how max pooling 

works, check out Chapter 

3

. Max pooling in 1D is similar to max pooling in 2D, except 

the sliding window only works in one dimension, going from left to right.

This is the list of parameters:

•