dvgodoy

from torch.utils.data import DataLoader

train_loader = DataLoader(dataset=train_data, batch_size=16, shuffle=True)

dvgodoy

from torch.utils.data import Dataset, TensorDataset

class CustomDataset(Dataset):
    def __init__(self, x_tensor, y_tensor):
        self.x = x_tensor
        self.y = y_tensor
        
    def __getitem__(self, index):
        return (self.x[index], self.y[index])

dvgodoy

class LayerLinearRegression(nn.Module):
    def __init__(self):
        super().__init__()
        # Instead of our custom parameters, we use a Linear layer with single input and single output
        self.linear = nn.Linear(1, 1)
                
    def forward(self, x):
        # Now it only takes a call to the layer to make predictions
        return self.linear(x)

dvgodoy

torch.manual_seed(42)

# Now we can create a model and send it at once to the device
model = ManualLinearRegression().to(device)
# We can also inspect its parameters using its state_dict
print(model.state_dict())

lr = 1e-1
n_epochs = 1000

dvgodoy

class ManualLinearRegression(nn.Module):
    def __init__(self):
        super().__init__()
        # To make "a" and "b" real parameters of the model, we need to wrap them with nn.Parameter
        self.a = nn.Parameter(torch.randn(1, requires_grad=True, dtype=torch.float))
        self.b = nn.Parameter(torch.randn(1, requires_grad=True, dtype=torch.float))
        
    def forward(self, x):
        # Computes the outputs / predictions
        return self.a + self.b * x

dvgodoy

torch.manual_seed(42)
a = torch.randn(1, requires_grad=True, dtype=torch.float, device=device)
b = torch.randn(1, requires_grad=True, dtype=torch.float, device=device)
print(a, b)

lr = 1e-1
n_epochs = 1000

# Defines a MSE loss function
loss_fn = nn.MSELoss(reduction='mean')

dvgodoy

torch.manual_seed(42)
a = torch.randn(1, requires_grad=True, dtype=torch.float, device=device)
b = torch.randn(1, requires_grad=True, dtype=torch.float, device=device)
print(a, b)

lr = 1e-1
n_epochs = 1000

# Defines a SGD optimizer to update the parameters
optimizer = optim.SGD([a, b], lr=lr)

dvgodoy

torch.manual_seed(42)
a = torch.randn(1, requires_grad=True, dtype=torch.float, device=device)
b = torch.randn(1, requires_grad=True, dtype=torch.float, device=device)

yhat = a + b * x_train_tensor
error = y_train_tensor - yhat
loss = (error ** 2).mean()

dvgodoy

lr = 1e-1
n_epochs = 1000

torch.manual_seed(42)
a = torch.randn(1, requires_grad=True, dtype=torch.float, device=device)
b = torch.randn(1, requires_grad=True, dtype=torch.float, device=device)

for epoch in range(n_epochs):
    yhat = a + b * x_train_tensor
    error = y_train_tensor - yhat

dvgodoy

# We can specify the device at the moment of creation - RECOMMENDED!
torch.manual_seed(42)
a = torch.randn(1, requires_grad=True, dtype=torch.float, device=device)
b = torch.randn(1, requires_grad=True, dtype=torch.float, device=device)
print(a, b)