File size: 2,362 Bytes
ad16788 |
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 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 |
import collections
from pathlib import Path
from typing import Union
import numpy as np
from typeguard import check_argument_types
from espnet2.fileio.read_text import load_num_sequence_text
class FloatRandomGenerateDataset(collections.abc.Mapping):
"""Generate float array from shape.txt.
Examples:
shape.txt
uttA 123,83
uttB 34,83
>>> dataset = FloatRandomGenerateDataset("shape.txt")
>>> array = dataset["uttA"]
>>> assert array.shape == (123, 83)
>>> array = dataset["uttB"]
>>> assert array.shape == (34, 83)
"""
def __init__(
self,
shape_file: Union[Path, str],
dtype: Union[str, np.dtype] = "float32",
loader_type: str = "csv_int",
):
assert check_argument_types()
shape_file = Path(shape_file)
self.utt2shape = load_num_sequence_text(shape_file, loader_type)
self.dtype = np.dtype(dtype)
def __iter__(self):
return iter(self.utt2shape)
def __len__(self):
return len(self.utt2shape)
def __getitem__(self, item) -> np.ndarray:
shape = self.utt2shape[item]
return np.random.randn(*shape).astype(self.dtype)
class IntRandomGenerateDataset(collections.abc.Mapping):
"""Generate float array from shape.txt
Examples:
shape.txt
uttA 123,83
uttB 34,83
>>> dataset = IntRandomGenerateDataset("shape.txt", low=0, high=10)
>>> array = dataset["uttA"]
>>> assert array.shape == (123, 83)
>>> array = dataset["uttB"]
>>> assert array.shape == (34, 83)
"""
def __init__(
self,
shape_file: Union[Path, str],
low: int,
high: int = None,
dtype: Union[str, np.dtype] = "int64",
loader_type: str = "csv_int",
):
assert check_argument_types()
shape_file = Path(shape_file)
self.utt2shape = load_num_sequence_text(shape_file, loader_type)
self.dtype = np.dtype(dtype)
self.low = low
self.high = high
def __iter__(self):
return iter(self.utt2shape)
def __len__(self):
return len(self.utt2shape)
def __getitem__(self, item) -> np.ndarray:
shape = self.utt2shape[item]
return np.random.randint(self.low, self.high, size=shape, dtype=self.dtype)
|