Ei1 n S SK r S SKJr S SKJrJrJrJr SSKJ r SSK
J r J r SSK
Jr " S S \5 rg)
N)Path)AnyCallableOptionalUnion )default_loader) download_and_extract_archiveverify_str_arg)
VisionDatasetc ^ \ rS rSrSrSrSrSSSS\4S\\ \
4 S \ S
\ \ S \ \ S \
S
\ \\ \
4 /\4 SS4U 4S jjjrS\4S jrS\S\\\4 4S jrS\ 4S jrS\
4S jrSS jrSrU =r$ )Food101 a `The Food-101 Data Set `_.
The Food-101 is a challenging data set of 101 food categories with 101,000 images.
For each class, 250 manually reviewed test images are provided as well as 750 training images.
On purpose, the training images were not cleaned, and thus still contain some amount of noise.
This comes mostly in the form of intense colors and sometimes wrong labels. All images were
rescaled to have a maximum side length of 512 pixels.
Args:
root (str or ``pathlib.Path``): Root directory of the dataset.
split (string, optional): The dataset split, supports ``"train"`` (default) and ``"test"``.
transform (callable, optional): A function/transform that takes in a PIL image or torch.Tensor, depends on the given loader,
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. Default is False.
loader (callable, optional): A function to load an image given its path.
By default, it uses PIL as its image loader, but users could also pass in
``torchvision.io.decode_image`` for decoding image data into tensors directly.
z1http://data.vision.ee.ethz.ch/cvl/food-101.tar.gz 85eeb15f3717b99a5da872d97d918f87trainNFrootsplit transformtarget_transformdownloadloaderreturnc > [ T U ] XUS9 [ USS5 U l [ U R
5 S- U l U R S- U l U R S- U l U( a U R 5 U R 5 ( d [ S5 e/ U l / U l
[ U R U S3- 5 n[ R " UR# 5 5 nS S S 5 [% WR' 5 5 U l [+ [- U R( [/ [1 U R( 5 5 5 5 U l UR5 5 H u pU =R U R2 U /[1 U
5 - -
sl U =R U
V s/ s H- oR R6 " U S 3R9 S
5 6 PM/ sn -
sl
M X`l g ! , ( d f GN
= fs sn f ) N)r r r )r testzfood-101metaimagesz;Dataset not found. You can use download=True to download itz.jsonz.jpg/) super__init__r _splitr r _base_folder _meta_folder_images_folder _download
_check_exists RuntimeError_labels _image_filesopenjsonloadsreadsortedkeysclassesdictziprangelen class_to_idxitemsjoinpathr r )
selfr r r r r r fmetadata class_label im_rel_paths im_rel_path __class__s
Y/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torchvision/datasets/food101.pyr Food101.__init__& s EUV$UG5FG Oj 8 - - 6 " / /( : NN !!## \] ]
$##uo5
6!zz!&&(+H 7 hmmo. T\\5T\\9J3K!L M)1 )9 %K LLT . .{ ; c , [ U R 5 $ N)r3 r( r7 s r> __len__Food101.__len__J s 4$$%% idxc U R U U R U p2U R U5 nU R ( a U R U5 nU R ( a U R U5 nXC4$ rA )r( r' r r r )r7 rF
image_filelabelimages r> __getitem__Food101.__getitem__M sa - -c 2DLL4EE J' >>NN5)E ))%0E|rE c SU R 3$ )Nzsplit=)r rB s r>
extra_reprFood101.extra_reprY s }%%rE c R [ S U R U R 4 5 5 $ )Nc 3 n # U H+ oR 5 =( a UR 5 v M- g 7frA )existsis_dir).0folders r> (Food101._check_exists..] s$ nEm6==?6v}}6Ems 35)allr" r# rB s r> r% Food101._check_exists\ s% ndFWFWY]YlYlEmnnnrE c U R 5 ( a g [ U R U R U R S9 g )N)
download_rootmd5)r% r
_URLr _MD5rB s r> r$ Food101._download_ s, $TYYdiiTYYWrE ) r! r( r# r' r" r r4 r/ r )r N)__name__
__module__ __qualname____firstlineno____doc__r] r^ r r strr r r boolr r intrC tuplerK rN r% r$ __static_attributes__
__classcell__)r= s @r> r r s . ?D -D
(,/3 4B" CI " " H% "
#8, "
" %T *+S01"
" " H& &
s
uS#X
&C &ot oX XrE r )r* pathlibr typingr r r r rU r utilsr
r visionr r rE r> rp s* 1 1 " ? !WXm WXrE