def _assert_no_grad(variable):
        assert not variable.requires_grad

    def forward(self, predicted, target):
        """
        Computes cross entropy between targets and predictions.
        """
        # No gradient over target
        _assert_no_grad(target)

        # Define variables
        p = predicted.clamp(0.01, 0.99)
        t = target.float()

        #Compute cross entropy
        h1 = p.log()*t
        h2 = (1-t)*((1-p).log())
        ce = torch.add(h1, h2)
        ce_out = torch.mean(ce, 1)
        ce_out = torch.mean(ce_out, 0)

        # Save for backward step
        self.save_for_backward(ce_out)

for t in range(50):

    print('Epoch {}'.format(t))
    if t > 0:
        print('Loss ->', loss)

    for batch_idx, (x_batch, y_batch) in enumerate(train_loader):
        # Wrap in Variable
        x_in, target = Variable(x_batch), Variable(y_batch)

        predicted = model(x_in)

        # Compute and print loss
        loss = criterion(predicted, target)

        # Zero gradients, perform a backward pass, and update the weights.
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()