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

Before Change

            nesterov = group["nesterov"]

            for p in group["params"]:
                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()
                    else:
                        buf = param_state["momentum_buffer"]
                        buf.mul_(momentum).add_(d_p, alpha=1 - dampening)
                    if nesterov:
                        d_p = d_p.add(buf, alpha=momentum)
                    else:

After Change

        for group in self.param_groups:
            params_with_grad = []
            d_p_list = []
            momentum_buffer_list = []
            weight_decay = group["weight_decay"]
            momentum = group["momentum"]
            dampening = group["dampening"]
            nesterov = group["nesterov"]
            lr = group["lr"]

            for p in group["params"]:
                if p.grad is not None:
                    params_with_grad.append(p)
                    d_p_list.append(p.grad)

                    state = self.state[p]
                    if "momentum_buffer" not in state:
                        momentum_buffer_list.append(None)
                    else:
                        momentum_buffer_list.append(state["momentum_buffer"])

            F.sgd(params_with_grad,
                  d_p_list,
                  momentum_buffer_list,
                  weight_decay,
                  momentum,
                  lr,
                  dampening,
                  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