# -*- coding: utf-8 -*-

# BSD 3-Clause License

#

# Copyright (c) 2017

# All rights reserved.

# Copyright 2022 Huawei Technologies Co., Ltd

#

# Redistribution and use in source and binary forms, with or without

# modification, are permitted provided that the following conditions are met:

#

# * Redistributions of source code must retain the above copyright notice, this

#   list of conditions and the following disclaimer.

#

# * Redistributions in binary form must reproduce the above copyright notice,

#   this list of conditions and the following disclaimer in the documentation

#   and/or other materials provided with the distribution.

#

# * Neither the name of the copyright holder nor the names of its

#   contributors may be used to endorse or promote products derived from

#   this software without specific prior written permission.

#

# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"

# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE

# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE

# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE

# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL

# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR

# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER

# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,

# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE

# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

# ==========================================================================





# Copyright (c) 2015-present, Facebook, Inc.

# All rights reserved.

import torch

import torch.distributed as dist

import math





class RASampler(torch.utils.data.Sampler):

    """Sampler that restricts data loading to a subset of the dataset for distributed,

    with repeated augmentation.

    It ensures that different each augmented version of a sample will be visible to a

    different process (GPU)

    Heavily based on torch.utils.data.DistributedSampler

    """



    def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True):

        if num_replicas is None:

            if not dist.is_available():

                raise RuntimeError("Requires distributed package to be available")

            num_replicas = dist.get_world_size()

        if rank is None:

            if not dist.is_available():

                raise RuntimeError("Requires distributed package to be available")

            rank = dist.get_rank()

        self.dataset = dataset

        self.num_replicas = num_replicas

        self.rank = rank

        self.epoch = 0

        self.num_samples = int(math.ceil(len(self.dataset) * 3.0 / self.num_replicas))

        self.total_size = self.num_samples * self.num_replicas

        # self.num_selected_samples = int(math.ceil(len(self.dataset) / self.num_replicas))

        self.num_selected_samples = int(math.floor(len(self.dataset) // 256 * 256 / self.num_replicas))

        self.shuffle = shuffle



    def __iter__(self):

        # deterministically shuffle based on epoch

        g = torch.Generator()

        g.manual_seed(self.epoch)

        if self.shuffle:

            indices = torch.randperm(len(self.dataset), generator=g).tolist()

        else:

            indices = list(range(len(self.dataset)))



        # add extra samples to make it evenly divisible

        indices = [ele for ele in indices for i in range(3)]

        indices += indices[:(self.total_size - len(indices))]

        assert len(indices) == self.total_size



        # subsample

        indices = indices[self.rank:self.total_size:self.num_replicas]

        assert len(indices) == self.num_samples



        return iter(indices[:self.num_selected_samples])



    def __len__(self):

        return self.num_selected_samples



    def set_epoch(self, epoch):

        self.epoch = epoch