Beginning Anomaly Detection Using

weight: (Optional) A tensor that’s the size of the number of classes 

n. This is essentially a weight given to each class so that some classes 

are weighted more heavily in how they affect the overall loss and 

optimization problem.

• 

size_average: (Deprecated in favor of reduction.) The losses are 

averaged over each loss element in the batch by default (True). If 

set to False, then the losses are summed for each minibatch instead. 

Default = True.

• 

ignore_index: (Optional) An integer that specifies a target value 

that is ignored so it does not contribute to the input gradient. If 

size_average is True, then the loss is averaged over targets that aren’t 

ignored.

• 

reduce: (Deprecated in favor of reduction.) The losses are averaged 

or summed over observations for each minibatch depending on size_

average by default (True). If set to False, it returns a loss per batch 

element and ignores size_average. Default = True.

• 

reduction: A string value to specify the type of reduction to be done. 

Choose between ‘none’, ‘elementwise_mean’, or ‘sum’. ‘none’ means 

no reduction is applied, ‘elementwise_mean’ will divide the sum of 

the output by the number of elements in the output, and ‘sum’ will 

just sum the output. Default = ’elementwise_mean’. Note: Specifying 

either size_average or reduce will override this parameter.

Figure B-30.  An alternate way to write the equation in Figure 

B-29

appendix B   intro to pytorch

---

390