try:
    from torch.optim import _functional as F
except:
    print("WARNING!!!, I recommend using torch>=1.8")

import torch
from torch.optim.optimizer import Optimizer
from mmcv.runner.optimizer.builder import OPTIMIZERS


@OPTIMIZERS.register_module()
class AdamW2(Optimizer):
    r"""Implements AdamW algorithm. Solve the bug of torch 1.8

    The original Adam algorithm was proposed in `Adam: A Method for Stochastic Optimization`_.
    The AdamW variant was proposed in `Decoupled Weight Decay Regularization`_.

    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 coefficient (default: 1e-2)
        amsgrad (boolean, optional): whether to use the AMSGrad variant of this
            algorithm from the paper `On the Convergence of Adam and Beyond`_
            (default: False)

    .. _Adam\: A Method for Stochastic Optimization:
        https://arxiv.org/abs/1412.6980
    .. _Decoupled Weight Decay Regularization:
        https://arxiv.org/abs/1711.05101
    .. _On the Convergence of Adam and Beyond:
        https://openreview.net/forum?id=ryQu7f-RZ
    """

    def __init__(
        self,
        params,
        lr=1e-3,
        betas=(0.9, 0.999),
        eps=1e-8,
        weight_decay=1e-2,
        amsgrad=False,
    ):
        if not 0.0 <= lr:
            raise ValueError("Invalid learning rate: {}".format(lr))
        if not 0.0 <= eps:
            raise ValueError("Invalid epsilon value: {}".format(eps))
        if not 0.0 <= betas[0] < 1.0:
            raise ValueError("Invalid beta parameter at index 0: {}".format(betas[0]))
        if not 0.0 <= betas[1] < 1.0:
            raise ValueError("Invalid beta parameter at index 1: {}".format(betas[1]))
        if not 0.0 <= weight_decay:
            raise ValueError("Invalid weight_decay value: {}".format(weight_decay))
        defaults = dict(
            lr=lr, betas=betas, eps=eps, weight_decay=weight_decay, amsgrad=amsgrad
        )
        super(AdamW2, self).__init__(params, defaults)

    def __setstate__(self, state):
        super(AdamW2, self).__setstate__(state)
        for group in self.param_groups:
            group.setdefault("amsgrad", 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 = []
            state_sums = []
            max_exp_avg_sqs = []
            state_steps = []
            amsgrad = group["amsgrad"]

            # put this line here for solving bug
            beta1, beta2 = group["betas"]

            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
                        )

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

                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
                state_steps.append(state["step"])

            F.adamw(
                params_with_grad,
                grads,
                exp_avgs,
                exp_avg_sqs,
                max_exp_avg_sqs,
                state_steps,
                amsgrad,
                beta1,
                beta2,
                group["lr"],
                group["weight_decay"],
                group["eps"],
            )

        return loss