// Create random Tensors for weights, and wrap them in Variables.
// Setting requires_grad=True indicates that we want to compute gradients with
// respect to these Variables during the backward pass.
w1 = Variable(torch.randn(D_in, H).type(dtype), requires_grad=True)
w2 = Variable(torch.randn(H, D_out).type(dtype), requires_grad=True)
learning_rate = 1e-6
After Change
// Create random Tensors to hold input and outputs.
// Setting requires_grad=False indicates that we do not need to compute gradients
// with respect to these Tensors during the backward pass.
x = torch.randn(N, D_in, device=device, dtype=dtype)
y = torch.randn(N, D_out, device=device, dtype=dtype)
// Create random Tensors for weights.
// Setting requires_grad=True indicates that we want to compute gradients with
// respect to these Tensors during the backward pass.
w1 = torch.randn(D_in, H, device=device, dtype=dtype, requires_grad=True)
w2 = torch.randn(H, D_out, device=device, dtype=dtype, requires_grad=True)
learning_rate = 1e-6
for t in range(500):
// Forward pass: compute predicted y using operations on Tensors; these
// are exactly the same operations we used to compute the forward pass using
// Tensors, but we do not need to keep references to intermediate values since
// we are not implementing the backward pass by hand.
y_pred = x.mm(w1).clamp(min=0).mm(w2)
// Compute and print loss using operations on Tensors.
// Now loss is a Tensor of shape (1,)
// loss.item() gets the a scalar value held in the loss.
loss = (y_pred - y).pow(2).sum()
print(t, loss.item())
// Use autograd to compute the backward pass. This call will compute the
// gradient of loss with respect to all Tensors with requires_grad=True.
