# Copyright (c) Facebook, Inc. and its affiliates.
# code from detectron2

import math
from typing import List
import torch

try:
    from torch.optim.lr_scheduler import LRScheduler
except ImportError:
    from torch.optim.lr_scheduler import _LRScheduler as LRScheduler

class WarmupCosineLR(LRScheduler):
    def __init__(
        self,
        optimizer: torch.optim.Optimizer,
        max_iters: int,
        warmup_factor: float = 0.001,
        warmup_iters: int = 1000,
        warmup_method: str = "linear",
        last_epoch: int = -1,
    ):
        self.max_iters = max_iters
        self.warmup_factor = warmup_factor
        self.warmup_iters = warmup_iters
        self.warmup_method = warmup_method
        super().__init__(optimizer, last_epoch)

    def get_lr(self) -> List[float]:
        warmup_factor = _get_warmup_factor_at_iter(
            self.warmup_method, self.last_epoch, self.warmup_iters, self.warmup_factor
        )
        # Different definitions of half-cosine with warmup are possible. For
        # simplicity we multiply the standard half-cosine schedule by the warmup
        # factor. An alternative is to start the period of the cosine at warmup_iters
        # instead of at 0. In the case that warmup_iters << max_iters the two are
        # very close to each other.
        return [
            base_lr
            * warmup_factor
            * 0.5
            * (1.0 + math.cos(math.pi * self.last_epoch / self.max_iters))
            for base_lr in self.base_lrs
        ]

    def _compute_values(self) -> List[float]:
        # The new interface
        return self.get_lr()


def _get_warmup_factor_at_iter(
    method: str, iter: int, warmup_iters: int, warmup_factor: float
) -> float:
    """
    Return the learning rate warmup factor at a specific iteration.
    See :paper:`ImageNet in 1h` for more details.

    Args:
        method (str): warmup method; either "constant" or "linear".
        iter (int): iteration at which to calculate the warmup factor.
        warmup_iters (int): the number of warmup iterations.
        warmup_factor (float): the base warmup factor (the meaning changes according
            to the method used).

    Returns:
        float: the effective warmup factor at the given iteration.
    """
    if iter >= warmup_iters:
        return 1.0

    if method == "constant":
        return warmup_factor
    elif method == "linear":
        alpha = iter / warmup_iters
        return warmup_factor * (1 - alpha) + alpha
    else:
        raise ValueError("Unknown warmup method: {}".format(method))

def build_lr_scheduler(cfg, optimizer, iters_per_epoch):
    max_iters = cfg['num_epoch'] * iters_per_epoch
    warmup_iters = int(cfg['warmup_epoch'] * iters_per_epoch)
    # warmup_iters = int(max_iters * 1/6)
    scheduler = WarmupCosineLR(
        optimizer,
        max_iters=max_iters,
        warmup_factor=cfg['warmup_factor'],
        warmup_iters=warmup_iters,
        warmup_method=cfg['warmup_method'],
        last_epoch=-1)
    return scheduler