Daniel Voigt Godoy - Deep Learning with PyTorch Step-by-Step A Beginner’s Guide-leanpub

Sequential Models
Our model was simple enough. You may be thinking: "Why even bother to build a
class for it?!" Well, you have a point…
For straightforward models that use a series of built-in PyTorch models (like
Linear), where the output of one is sequentially fed as an input to the next, we can
use a, er … Sequential model :-)
In our case, we would build a sequential model with a single argument; that is, the
Linear model we used to train our linear regression. The model would look like
this:
Notebook Cell 1.12 - Building a model using PyTorch’s Sequential model
1 torch.manual_seed(42)
2 # Alternatively, you can use a Sequential model
3 model = nn.Sequential(nn.Linear(1, 1)).to(device)
4
5 model.state_dict()
Output
OrderedDict([('0.weight', tensor([[0.7645]], device='cuda:0')),
('0.bias', tensor([0.8300], device='cuda:0'))])
Simple enough, right?
We’ve been talking about models inside other models. This may get confusing real
quick, so let’s follow convention and call any internal model a layer.
112 | Chapter 1: A Simple Regression Problem