adamax.py 文件源码

def step(self, closure=None):
        """Performs a single optimization step.

        Arguments:
            closure (callable, optional): A closure that reevaluates the model
                and returns the loss.
        """
        loss = None
        if closure is not None:
            loss = closure()

        for group in self.param_groups:
            for p in group['params']:
                if p.grad is None:
                    continue
                grad = p.grad.data
                if grad.is_sparse:
                    raise RuntimeError('Adamax does not support sparse gradients')
                state = self.state[p]

                # State initialization
                if len(state) == 0:
                    state['step'] = 0
                    state['exp_avg'] = torch.zeros_like(p.data)
                    state['exp_inf'] = torch.zeros_like(p.data)

                exp_avg, exp_inf = state['exp_avg'], state['exp_inf']
                beta1, beta2 = group['betas']
                eps = group['eps']

                state['step'] += 1

                if group['weight_decay'] != 0:
                    grad = grad.add(group['weight_decay'], p.data)

                # Update biased first moment estimate.
                exp_avg.mul_(beta1).add_(1 - beta1, grad)
                # Update the exponentially weighted infinity norm.
                norm_buf = torch.cat([
                    exp_inf.mul_(beta2).unsqueeze(0),
                    grad.abs().add_(eps).unsqueeze_(0)
                ], 0)
                torch.max(norm_buf, 0, keepdim=False, out=(exp_inf, exp_inf.new().long()))

                bias_correction = 1 - beta1 ** state['step']
                clr = group['lr'] / bias_correction

                p.data.addcdiv_(-clr, exp_avg, exp_inf)

        return loss