Spaces:
Running
on
Zero
Running
on
Zero
File size: 3,883 Bytes
28c256d |
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 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 |
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
from typing import Sequence, Union
import mmengine
import numpy as np
import torch
from .base import BaseTransform
from .builder import TRANSFORMS
def to_tensor(
data: Union[torch.Tensor, np.ndarray, Sequence, int,
float]) -> torch.Tensor:
"""Convert objects of various python types to :obj:`torch.Tensor`.
Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`,
:class:`Sequence`, :class:`int` and :class:`float`.
Args:
data (torch.Tensor | numpy.ndarray | Sequence | int | float): Data to
be converted.
Returns:
torch.Tensor: the converted data.
"""
if isinstance(data, torch.Tensor):
return data
elif isinstance(data, np.ndarray):
return torch.from_numpy(data)
elif isinstance(data, Sequence) and not mmengine.is_str(data):
return torch.tensor(data)
elif isinstance(data, int):
return torch.LongTensor([data])
elif isinstance(data, float):
return torch.FloatTensor([data])
else:
raise TypeError(f'type {type(data)} cannot be converted to tensor.')
@TRANSFORMS.register_module()
class ToTensor(BaseTransform):
"""Convert some results to :obj:`torch.Tensor` by given keys.
Required keys:
- all these keys in `keys`
Modified Keys:
- all these keys in `keys`
Args:
keys (Sequence[str]): Keys that need to be converted to Tensor.
"""
def __init__(self, keys: Sequence[str]) -> None:
self.keys = keys
def transform(self, results: dict) -> dict:
"""Transform function to convert data to `torch.Tensor`.
Args:
results (dict): Result dict from loading pipeline.
Returns:
dict: `keys` in results will be updated.
"""
for key in self.keys:
key_list = key.split('.')
cur_item = results
for i in range(len(key_list)):
if key_list[i] not in cur_item:
raise KeyError(f'Can not find key {key}')
if i == len(key_list) - 1:
cur_item[key_list[i]] = to_tensor(cur_item[key_list[i]])
break
cur_item = cur_item[key_list[i]]
return results
def __repr__(self) -> str:
return self.__class__.__name__ + f'(keys={self.keys})'
@TRANSFORMS.register_module()
class ImageToTensor(BaseTransform):
"""Convert image to :obj:`torch.Tensor` by given keys.
The dimension order of input image is (H, W, C). The pipeline will convert
it to (C, H, W). If only 2 dimension (H, W) is given, the output would be
(1, H, W).
Required keys:
- all these keys in `keys`
Modified Keys:
- all these keys in `keys`
Args:
keys (Sequence[str]): Key of images to be converted to Tensor.
"""
def __init__(self, keys: dict) -> None:
self.keys = keys
def transform(self, results: dict) -> dict:
"""Transform function to convert image in results to
:obj:`torch.Tensor` and transpose the channel order.
Args:
results (dict): Result dict contains the image data to convert.
Returns:
dict: The result dict contains the image converted
to :obj:``torch.Tensor`` and transposed to (C, H, W) order.
"""
for key in self.keys:
img = results[key]
if len(img.shape) < 3:
img = np.expand_dims(img, -1)
results[key] = (to_tensor(img.transpose(2, 0, 1))).contiguous()
return results
def __repr__(self) -> str:
return self.__class__.__name__ + f'(keys={self.keys})'
|