Method step

ldm/util.py:119–197

Performs a single optimization step. Args: closure (callable, optional): A closure that reevaluates the model and returns the loss.

(self, closure=None)

    @torch.no_grad()
    def step(self, closure=None):
        """Performs a single optimization step.
        Args:
            closure (callable, optional): A closure that reevaluates the model
                and returns the loss.
        """
        loss = None
        if closure is not None:
            with torch.enable_grad():
                loss = closure()

        for group in self.param_groups:
            params_with_grad = []
            grads = []
            exp_avgs = []
            exp_avg_sqs = []
            ema_params_with_grad = []
            state_sums = []
            max_exp_avg_sqs = []
            state_steps = []
            amsgrad = group['amsgrad']
            beta1, beta2 = group['betas']
            ema_decay = group['ema_decay']
            ema_power = group['ema_power']

            for p in group['params']:
                if p.grad is None:
                    continue
                params_with_grad.append(p)
                if p.grad.is_sparse:
                    raise RuntimeError('AdamW does not support sparse gradients')
                grads.append(p.grad)

                state = self.state[p]

                # State initialization
                if len(state) == 0:
                    state['step'] = 0
                    # Exponential moving average of gradient values
                    state['exp_avg'] = torch.zeros_like(p, memory_format=torch.preserve_format)
                    # Exponential moving average of squared gradient values
                    state['exp_avg_sq'] = torch.zeros_like(p, memory_format=torch.preserve_format)
                    if amsgrad:
                        # Maintains max of all exp. moving avg. of sq. grad. values
                        state['max_exp_avg_sq'] = torch.zeros_like(p, memory_format=torch.preserve_format)
                    # Exponential moving average of parameter values
                    state['param_exp_avg'] = p.detach().float().clone()

                exp_avgs.append(state['exp_avg'])
                exp_avg_sqs.append(state['exp_avg_sq'])
                ema_params_with_grad.append(state['param_exp_avg'])

                if amsgrad:
                    max_exp_avg_sqs.append(state['max_exp_avg_sq'])

                # update the steps for each param group update
                state['step'] += 1
                # record the step after step update