Beginning Anomaly Detection Using

model: An instance of a model class. In this case, it’s an instance of 

the CNN class defined above.

• 

device: This basically tells PyTorch what device (if the GPU is an 

option, which GPU to run on, and if not, the CPU is the device) to run 

on. In this case, you define the device right after the imports.

• 

test_loader: The loader for the testing data set. In this case, you use 

a data_loader because that’s how the MNIST data is formatted when 

importing from torchvision. This data loader contains the testing 

samples for the MNIST data set.

Now you can get to defining your hyperparameters and data loaders, and calling 

your train and test functions (Figures 

B-11

 through 

B-13

).

Figure B-10.  The code in Figure 

B-9

 in a Jupyter cell

appendix B   intro to pytorch

---

372

+\SHUSDUDPHWHUV

QXPBHSRFKV 

QXPBFODVVHV 

EDWFKBVL]H 

OHDUQLQJBUDWH 

/RDG01,67GDWDVHW

WUDLQBGDWDVHW WRUFKYLVLRQGDWDVHWV01,67 URRW GDWD 

WUDLQ