Pure SGD in PyTOrch

pure_sgd.py

# https://github.com/jcjohnson/pytorch-examples
for t in range(500):
  # Forward pass: compute predicted y by passing x to the model. Module objects
  # override the __call__ operator so you can call them like functions. When
  # doing so you pass a Variable of input data to the Module and it produces
  # a Variable of output data.
  y_pred = model(x)

  # Compute and print loss. We pass Variables containing the predicted and true
  # values of y, and the loss function returns a Variable containing the loss.
  loss = loss_fn(y_pred, y)
  print(t, loss.data[0])
  
  # Zero the gradients before running the backward pass.
  model.zero_grad()

  # Backward pass: compute gradient of the loss with respect to all the learnable
  # parameters of the model. Internally, the parameters of each Module are stored
  # in Variables with requires_grad=True, so this call will compute gradients for
  # all learnable parameters in the model.
  loss.backward()

  # Update the weights using gradient descent. Each parameter is a Variable, so
  # we can access its data and gradients like we did before.
  for param in model.parameters():
    param.data -= learning_rate * param.grad.data