__init__.py 1.5 KB
Newer Older
1
# Copyright (c) 2017-2019 NVIDIA CORPORATION. All rights reserved.
H
huangyuxin 已提交
2
# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
3 4 5 6 7 8 9 10 11 12 13 14
# See the LICENSE file for licensing terms (BSD-style).
# Modified from https://github.com/webdataset/webdataset
#
# flake8: noqa

from .cache import (
    cached_tarfile_samples,
    cached_tarfile_to_samples,
    lru_cleanup,
    pipe_cleaner,
)
from .compat import WebDataset, WebLoader, FluidWrapper
H
huangyuxin 已提交
15
from .extradatasets import MockDataset, with_epoch, with_length
16 17 18 19 20 21 22 23 24 25 26 27 28 29
from .filters import (
    associate,
    batched,
    decode,
    detshuffle,
    extract_keys,
    getfirst,
    info,
    map,
    map_dict,
    map_tuple,
    pipelinefilter,
    rename,
    rename_keys,
H
huangyuxin 已提交
30
    audio_resample,
31 32 33 34 35 36 37
    select,
    shuffle,
    slice,
    to_tuple,
    transform_with,
    unbatched,
    xdecode,
H
huangyuxin 已提交
38 39 40 41 42
    audio_data_filter,
    audio_tokenize,
    audio_resample,
    audio_compute_fbank,
    audio_spec_aug,
43
    sort,
H
huangyuxin 已提交
44 45
    audio_padding,
    audio_cmvn,
46
    placeholder,
47
)
48
from .handlers import (
49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68
    ignore_and_continue,
    ignore_and_stop,
    reraise_exception,
    warn_and_continue,
    warn_and_stop,
)
from .pipeline import DataPipeline
from .shardlists import (
    MultiShardSample,
    ResampledShards,
    SimpleShardList,
    non_empty,
    resampled,
    shardspec,
    single_node_only,
    split_by_node,
    split_by_worker,
)
from .tariterators import tarfile_samples, tarfile_to_samples
from .utils import PipelineStage, repeatedly
H
huangyuxin 已提交
69 70
from .writer import ShardWriter, TarWriter, numpy_dumps
from .mix import RandomMix, RoundRobin