data_loader.py

# BSD 3-Clause License
#
# Copyright (C) 2021 THL A29 Limited, a Tencent company.  All rights reserved.
#
# 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 psutil authors 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 OWNER 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.

import torch
from torch.utils.data import SequentialSampler


def get_bert_data_loader(
    batch_size,
    total_samples,
    sequence_length,
    device,
    data_type=torch.float,
    is_distrbuted=False,
):
    train_data = torch.randint(
        low=0,
        high=1000,
        size=(total_samples, sequence_length),
        device=device,
        dtype=torch.long,
    )
    train_label = torch.randint(
        low=0, high=2, size=(total_samples,), device=device, dtype=torch.long
    )
    train_dataset = torch.utils.data.TensorDataset(train_data, train_label)
    if is_distrbuted:
        sampler = torch.utils.data.distributed.DistributedSampler(train_dataset)
    else:
        sampler = SequentialSampler(train_dataset)
    train_loader = torch.utils.data.DataLoader(
        train_dataset, batch_size=batch_size, sampler=sampler
    )
    return train_loader