Eih r S SK Jr S SKrS SKJr S SKJrJr SSKJ r SSK
J r J r SSK
Jr " S S
\5 rg) ) annotationsN)Path)AnyCallable )default_loader) download_and_extract_archiveverify_str_arg)
VisionDatasetc ^ \ rS rSrSrSrSSSSS\4 SU 4S jjjrSS jrSS
jr SS jr
SS jr S
r U =r
$ ) FGVCAircraft
a `FGVC Aircraft `_ Dataset.
The dataset contains 10,000 images of aircraft, with 100 images for each of 100
different aircraft model variants, most of which are airplanes.
Aircraft models are organized in a three-levels hierarchy. The three levels, from
finer to coarser, are:
- ``variant``, e.g. Boeing 737-700. A variant collapses all the models that are visually
indistinguishable into one class. The dataset comprises 100 different variants.
- ``family``, e.g. Boeing 737. The dataset comprises 70 different families.
- ``manufacturer``, e.g. Boeing. The dataset comprises 30 different manufacturers.
Args:
root (str or ``pathlib.Path``): Root directory of the FGVC Aircraft dataset.
split (string, optional): The dataset split, supports ``train``, ``val``,
``trainval`` and ``test``.
annotation_level (str, optional): The annotation level, supports ``variant``,
``family`` and ``manufacturer``.
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.
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.
zWhttps://www.robots.ox.ac.uk/~vgg/data/fgvc-aircraft/archives/fgvc-aircraft-2013b.tar.gztrainvalvariantNFc
> > [ TU ] XUS9 [ USS5 U l [ USS5 U l [
R R U R S5 U l U( a U R 5 U R 5 ( d [ S5 e[
R R U R SS S
S S.U R 5 n[ U5 n U V
s/ s H oR 5 PM sn
U l S S S 5 [! [# U R [% [' U R 5 5 5 5 U l [
R R U R SS 5 n [
R R U R SS
U R SU R S35 n / U l / U l [ U 5 n U H n
U
R 5 R/ SS5 u pU R* R1 [
R R X S35 5 U R, R1 U R( U 5 M S S S 5 Xpl g s sn
f ! , ( d f GN|= f! , ( d f N,= f)N) transformtarget_transformsplit)trainvalr testannotation_level)r family manufacturerzfgvc-aircraft-2013bz;Dataset not found. You can use download=True to download itdataz variants.txtz families.txtzmanufacturers.txtimagesimages__z.txt r z.jpg)super__init__r
_split_annotation_levelospathjoinroot
_data_path _download
_check_exists RuntimeErroropenstripclassesdictziprangelen class_to_idx _image_files_labelsr appendloader)selfr' r r r r downloadr7 annotation_fileflineimage_data_folder labels_file
image_name
label_name __class__s _/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torchvision/datasets/fgvc_aircraft.pyr! FGVCAircraft.__init__. s EUV$UG5YZ !/ 02W"
'',,tyy2GH NN !!## \] ] '',, OO )( 3
$$
&
/
"a567QTJJLQ7DL # !T\\5T\\9J3K!L M GGLL &( Kggll4??FgdF\F\E]]^_c_j_j^kko>NN5)E ))%0E|rI c p U R 5 ( a g[ U R U R 5 g)zG
Download the FGVC Aircraft dataset archive and extract it under root.
N)r* r _URLr' rF s rB r) FGVCAircraft._downloado s( $TYY :rI c [ R R U R 5 =( a) [ R R U R 5 $ rE )r$ r% existsr( isdirrF s rB r* FGVCAircraft._check_existsw s/ ww~~doo.Q277== 3QQrI )r# r( r4 r5 r" r3 r. r7 )r' z
str | Pathr strr rX r Callable | Noner rY r9 boolr7 zCallable[[str], Any]returnNone)r[ int)rK r] r[ ztuple[Any, Any])r[ r\ )r[ rZ )__name__
__module__ __qualname____firstlineno____doc__rR r r! rG rO r) r* __static_attributes__
__classcell__)rA s @rB r
r
s < eD
)%),0 '50 0 0 0
# 0 *
0 0 %0
0 0 d&
;R RrI r
)
__future__r r$ pathlibr typingr r folderr utilsr r
visionr r
rI rB rl s* " " ? !kR= kRrI