torch.optim.Adam() 函数用法

Adam: A method for stochastic optimization

 Adam是通过梯度的一阶矩和二阶矩自适应的控制每个参数的学习率的大小。

 adam的初始化

    def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8,
                 weight_decay=0, amsgrad=False):

Args:
    params (iterable): iterable of parameters to optimize or dicts defining
        parameter groups
    lr (float, optional): learning rate (default: 1e-3)
    betas (Tuple[float, float], optional): coefficients used for computing
        running averages of gradient and its square (default: (0.9, 0.999))
    eps (float, optional): term added to the denominator to improve
        numerical stability (default: 1e-8)
    weight_decay (float, optional): weight decay (L2 penalty) (default: 0)
    amsgrad (boolean, optional): whether to use the AMSGrad variant of this
        algorithm from the paper `On the Convergence of Adam and Beyond`_
        (default: False)

@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 = []
            max_exp_avg_sqs = []
            state_steps = []
            beta1, beta2 = group['betas']

            for p in group['params']:
                if p.grad is not None:
                    params_with_grad.append(p)
                    if p.grad.is_sparse:
                        raise RuntimeError('Adam does not support sparse gradients, please consider SparseAdam instead')
                    grads.append(p.grad)

                    state = self.state[p]
                    # Lazy 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 group['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)

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

                    if group['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
                    state_steps.append(state['step'])

            F.adam(params_with_grad,
                   grads,
                   exp_avgs,
                   exp_avg_sqs,
                   max_exp_avg_sqs,
                   state_steps,
                   amsgrad=group['amsgrad'],
                   beta1=beta1,
                   beta2=beta2,
                   lr=group['lr'],
                   weight_decay=group['weight_decay'],
                   eps=group['eps'])
        return loss