Dih r d dl mZ d dlZd dlmZ d dlmZmZ ddlm Z ddl
m Z m Z ddl
mZ G d d
e Zy) ) annotationsN)Path)AnyCallable )default_loader) download_and_extract_archiveverify_str_arg)
VisionDatasetc t e Zd ZdZdZdddddef d fd
Zd
dZdd Zdd
Z dd Z
xZ S ) FGVCAircrafta2 `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
, t | ||| t |dd | _ t |dd | _ t
j j | j d | _ |r| j | j s t d t
j j | j dd d
d d| j }t | 5 } | D
cg c] }
|
j c}
| _ d d d t! t# | j t% t' | j | _ t
j j | j dd } t
j j | j dd
| j d| j d } g | _ g | _ t | 5 } | D ] }
|
j j/ dd \ }
}| j* j1 t
j j | |
d | j, j1 | j( | d d d || _ y c c}
w # 1 sw Y yxY w# 1 sw Y || _ y xY w)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 downloadr6 annotation_fileflineimage_data_folder labels_file
image_name
label_name __class__s d/var/www/pod-logistic/pod-ai/venv/lib/python3.12/site-packages/torchvision/datasets/fgvc_aircraft.pyr zFGVCAircraft.__init__. s- EUV$UG5YZ !/ 02W"
'',,tyy2GH NN !!# \] ] '',, OO )( 3
$$
&
/
" 8a567TDJJL7DL 8 !T\\5T\\9J3K!L M GGLL &( Kggll4??FgdF\F\E]]^_c_j_j^kko>NN5)E ))%0Ee|rF c f | j ryt | j | j y)zW
Download the FGVC Aircraft dataset archive and extract it under root.
N)r) r _URLr& rD s rA r( zFGVCAircraft._downloado s% $TYY :rF c t j j | j xr) t j j | j S rC )r# r$ existsr' isdirrD s rA r) zFGVCAircraft._check_existsw s/ ww~~doo.Q277== 3QQrF )r& z
str | Pathr strr rR r Callable | Noner rS r8 boolr6 zCallable[[str], Any]returnNone)rU int)rH rW rU ztuple[Any, Any])rU rV )rU rT ) __name__
__module__ __qualname____doc__rN r r rE rL r( r)
__classcell__)r@ s @rA r
r
s < eD
)%),0 '50 0 0 0
# 0 *
0 0 %0
0 d&
;RrF r
)
__future__r r# pathlibr typingr r folderr utilsr r
visionr r
rF rA rd s* " " ? !kR= kRrF