File size: 2,381 Bytes
af758d1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 |
# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import time
import torch
from src.models.data.provider import Provider
def get_multi_dataloader(opt, accelerator=None):
train_datasets, test_datasets = get_datasets(opt, accelerator)
train_dataset = torch.utils.data.ConcatDataset(train_datasets)
train_dataloader = torch.utils.data.DataLoader(
train_dataset,
batch_size=opt.batch_size,
shuffle=True,
num_workers=opt.num_workers,
pin_memory=True,
drop_last=True,
)
test_dataset = torch.utils.data.ConcatDataset(test_datasets)
test_dataloader = torch.utils.data.DataLoader(
test_dataset,
batch_size=opt.batch_size,
shuffle=False,
num_workers=opt.num_workers,
pin_memory=True,
drop_last=False,
)
return train_dataloader, test_dataloader
def get_datasets(opt, accelerator=None):
train_datasets = []
test_datasets = []
for idx in range(len(opt.data_mode)):
begin_time = time.time()
if isinstance(opt.data_mode[idx], str):
dataset_name, num_repeat = opt.data_mode[idx], 1
else:
dataset_name, num_repeat = opt.data_mode[idx]
train_dataset = Provider(dataset_name, opt, training=True, num_repeat=num_repeat)
train_datasets.append(train_dataset)
test_dataset = Provider(dataset_name, opt, training=False, num_repeat=num_repeat)
test_datasets.append(test_dataset)
if accelerator is None or accelerator.is_main_process:
print(f"Loaded {dataset_name}, train size: {len(train_dataset)}, test size: {len(test_dataset)}, loading took {time.time() - begin_time} seconds")
return train_datasets, test_datasets
|