1 import torch
 2 
 3 # N is batch size; D_in is input dimension;
 4 # H is hidden dimension; D_out is output dimension.
 5 N, D_in, H, D_out=64, 1000, 100, 10
 6 
 7 # Create random Tensors to hold inputs and outputs
 8 x= torch.randn(N, D_in)
 9 y= torch.randn(N, D_out)
10 
11 # Use the nn package to define our model and loss function.
12 model= torch.nn.Sequential(
13     torch.nn.Linear(D_in, H),
14     torch.nn.ReLU(),
15     torch.nn.Linear(H, D_out),
16 )
17 loss_fn=torch.nn.MSELoss(reduction='sum')
18 
19 # Use the optim package to define an Optimizer that will update the weights of
20 # the model for us. Here we will use Adam; the optim package contains many other
21 # optimization algoriths. The first argument to the Adam constructor tells the
22 # optimizer which Tensors it should update.
23 learning_rate=1e-4
24 optimizer=torch.optim.Adam(model.parameters(), lr=learning_rate)
25 for t in range(500):
26     # Forward pass: compute predicted y by passing x to the model.
27     y_pred= model(x)
28 
29     # Compute and print loss.
30     loss= loss_fn(y_pred, y)
31     print(t, loss.item())
32 
33     # Before the backward pass, use the optimizer object to zero all of the
34     # gradients for the variables it will update (which are the learnable
35     # weights of the model). This is because by default, gradients are
36     # accumulated in buffers( i.e, not overwritten) whenever .backward()
37     # is called. Checkout docs of torch.autograd.backward for more details.
38     optimizer.zero_grad()
39 
40     # Backward pass: compute gradient of the loss with respect to model
41     # parameters
42     loss.backward()
43 
44     # Calling the step function on an Optimizer makes an update to its
45     # parameters
46     optimizer.step()