42. Make Predictions with Model

[ishashankkawle]

As I am following the course, I have implemented basic model with very basic forward() for LinearRegressionModel() as below

# Create a Linear Regression model class
class LinearRegressionModel(nn.Module): # <- almost everything in PyTorch is a nn.Module (think of this as neural network lego blocks)
    def __init__(self):
        super().__init__() 
        self.weights = nn.Parameter(torch.randn(1, # <- start with random weights (this will get adjusted as the model learns)
                                                dtype=torch.float), # <- PyTorch loves float32 by default
                                   requires_grad=True) # <- can we update this value with gradient descent?)

        self.bias = nn.Parameter(torch.randn(1, # <- start with random bias (this will get adjusted as the model learns)
                                            dtype=torch.float), # <- PyTorch loves float32 by default
                                requires_grad=True) # <- can we update this value with gradient descent?))

    # Forward defines the computation in the model
    def forward(self, x: torch.Tensor) -> torch.Tensor: # <- "x" is the input data (e.g. training/testing features)
        return self.weights * x + self.bias # <- this is the linear regression formula (y = m*x + b)

What I am not understanding is when we create an object of class and try to do prediction in inference mode, how is it triggering the forward method in below code?

# Set manual seed since nn.Parameter are randomly initialized
torch.manual_seed(42)

# Create an instance of the model (this is a subclass of nn.Module that contains nn.Parameter(s))
model_0 = LinearRegressionModel()

# Make predictions with model
with torch.inference_mode(): 
    y_preds = model_0(X_test)
y_preds

Also how can we access y_preds outside of with block as it was defined inside it?
Sorry, I am new to Python so I may be missing out on some fundamentals. TIA !!

[37Lime]

Hi there,

What I am not understanding is when we create an object of class and try to do prediction in inference mode, how is it triggering the forward method in below code?

This is because a __call__() method is defined in nn.Module.

For the second question, with torch.inference_mode(): alters properties related to training. You can read more about it in the documentation. If it is the with part of the statement you want to know more about, have a look at this discussion.

Best wishes.