You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

93 lines
3.1 KiB

5 months ago
import os.path
from pathlib import Path
from typing import Any, Callable, Optional, Tuple, Union
import numpy as np
from PIL import Image
from .utils import check_integrity, download_url
from .vision import VisionDataset
class SEMEION(VisionDataset):
r"""`SEMEION <http://archive.ics.uci.edu/ml/datasets/semeion+handwritten+digit>`_ Dataset.
Args:
root (str or ``pathlib.Path``): Root directory of dataset where directory
``semeion.py`` exists.
transform (callable, optional): A function/transform that takes in a PIL image
and returns a transformed version. E.g, ``transforms.RandomCrop``
target_transform (callable, optional): A function/transform that takes in the
target and transforms it.
download (bool, optional): If true, downloads the dataset from the internet and
puts it in root directory. If dataset is already downloaded, it is not
downloaded again.
"""
url = "http://archive.ics.uci.edu/ml/machine-learning-databases/semeion/semeion.data"
filename = "semeion.data"
md5_checksum = "cb545d371d2ce14ec121470795a77432"
def __init__(
self,
root: Union[str, Path],
transform: Optional[Callable] = None,
target_transform: Optional[Callable] = None,
download: bool = True,
) -> None:
super().__init__(root, transform=transform, target_transform=target_transform)
if download:
self.download()
if not self._check_integrity():
raise RuntimeError("Dataset not found or corrupted. You can use download=True to download it")
fp = os.path.join(self.root, self.filename)
data = np.loadtxt(fp)
# convert value to 8 bit unsigned integer
# color (white #255) the pixels
self.data = (data[:, :256] * 255).astype("uint8")
self.data = np.reshape(self.data, (-1, 16, 16))
self.labels = np.nonzero(data[:, 256:])[1]
def __getitem__(self, index: int) -> Tuple[Any, Any]:
"""
Args:
index (int): Index
Returns:
tuple: (image, target) where target is index of the target class.
"""
img, target = self.data[index], int(self.labels[index])
# doing this so that it is consistent with all other datasets
# to return a PIL Image
img = Image.fromarray(img, mode="L")
if self.transform is not None:
img = self.transform(img)
if self.target_transform is not None:
target = self.target_transform(target)
return img, target
def __len__(self) -> int:
return len(self.data)
def _check_integrity(self) -> bool:
root = self.root
fpath = os.path.join(root, self.filename)
if not check_integrity(fpath, self.md5_checksum):
return False
return True
def download(self) -> None:
if self._check_integrity():
print("Files already downloaded and verified")
return
root = self.root
download_url(self.url, root, self.filename, self.md5_checksum)