a0cf5566d88533c5caa7a490beb6eb0760eee9b4,torch/optim/sgd.py,SGD,step,#SGD#Any#,76

Before Change

                if p.grad is None:
                    continue
                d_p = p.grad
                if weight_decay != 0:
                    d_p = d_p.add(p, alpha=weight_decay)
                if momentum != 0:
                    param_state = self.state[p]
                    if "momentum_buffer" not in param_state:
                        buf = param_state["momentum_buffer"] = torch.clone(d_p).detach()

After Change

                  nesterov)

            // update momentum_buffers in state
            for p, momentum_buffer in zip(params_with_grad, momentum_buffer_list):
                state = self.state[p]
                state["momentum_buffer"] = momentum_buffer

        return loss

Instances