scheduler.py

# © 2022. Triad National Security, LLC. All rights reserved.

# This program was produced under U.S. Government contract 89233218CNA000001 for Los Alamos

# National Laboratory (LANL), which is operated by Triad National Security, LLC for the U.S.

# Department of Energy/National Nuclear Security Administration. All rights in the program are

# reserved by Triad National Security, LLC, and the U.S. Department of Energy/National Nuclear

# Security Administration. The Government is granted for itself and others acting on its behalf a

# nonexclusive, paid-up, irrevocable worldwide license in this material to reproduce, prepare

# derivative works, distribute copies to the public, perform publicly and display publicly, and to permit

# others to do so.

import torch
from bisect import bisect_right

# Scheduler adopted from the original repo
class WarmupMultiStepLR(torch.optim.lr_scheduler._LRScheduler):
    def __init__(
        self,
        optimizer,
        milestones,
        gamma=0.1,
        warmup_factor=1.0 / 3,
        warmup_iters=5,
        warmup_method="linear",
        last_epoch=-1,
    ):
        if not milestones == sorted(milestones):
            raise ValueError(
                "Milestones should be a list of" " increasing integers. Got {}",
                milestones,
            )

        if warmup_method not in ("constant", "linear"):
            raise ValueError(
                "Only 'constant' or 'linear' warmup_method accepted"
                "got {}".format(warmup_method)
            )
        self.milestones = milestones
        self.gamma = gamma
        self.warmup_factor = warmup_factor
        self.warmup_iters = warmup_iters
        self.warmup_method = warmup_method
        super(WarmupMultiStepLR, self).__init__(optimizer, last_epoch)

    def get_lr(self):
        warmup_factor = 1
        if self.last_epoch < self.warmup_iters:
            if self.warmup_method == "constant":
                warmup_factor = self.warmup_factor
            elif self.warmup_method == "linear":
                alpha = float(self.last_epoch) / self.warmup_iters
                warmup_factor = self.warmup_factor * (1 - alpha) + alpha
        return [
            base_lr *
            warmup_factor *
            self.gamma ** bisect_right(self.milestones, self.last_epoch)
            for base_lr in self.base_lrs
        ]