Yhh z d dl mZ d dlZd dlmZ d dlmZmZ ddlm Z ddl
m Z m Z ddl
mZ G d d
e ZdS ) ) annotationsN)Path)AnyCallable )default_loader) download_and_extract_archiveverify_str_arg)
VisionDatasetc V e Zd ZdZdZdddddefd fd
Zd dZd dZd dZ d!d 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.gztrainvalvariantNFroot
str | Pathsplitstrannotation_level transformCallable | Nonetarget_transformdownloadboolloaderCallable[[str], Any]returnNonec
( t ||| t |dd | _ t |dd | _ t
j | j d | _ |r|
| st d t
j | j dd d
d d| j }t | 5 } d | D | _ d d d n # 1 swxY w Y t t! | j t# t% | j | _ t
j | j dd
}
t
j | j dd| j d| j d } g | _ g | _ t | 5 } | D ]} | dd \ }
}| j t
j |
|
d | j | j | d d d n # 1 swxY w Y || _ d S )N)r r r )trainvalr testr )r family manufacturerzfgvc-aircraft-2013bz;Dataset not found. You can use download=True to download itdataz variants.txtz families.txtzmanufacturers.txtc 6 g | ]}| S )strip).0lines t/var/www/tools.fuzzalab.pt/emblema-extractor/venv/lib/python3.11/site-packages/torchvision/datasets/fgvc_aircraft.py
z)FGVCAircraft.__init__..O s 777TDJJLL777 imagesimages__z.txt r z.jpg)super__init__r
_split_annotation_levelospathjoinr
_data_path _download
_check_exists RuntimeErroropenclassesdictziprangelen class_to_idx _image_files_labelsr' r appendr )selfr r r r r r r annotation_filefimage_data_folder labels_filer)
image_name
label_name __class__s r* r2 zFGVCAircraft.__init__. s EUVVV$UG5YZZ !/ 02W"
"
',,ty2GHH NN !!## ^ \]] ] ',, O )( 3
$
&
/
"
" 8a77Q777DL 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 !T\5T\9J9J3K3K!L!L M M GLL &( K Kgll4?F *NN5))E 1))%00Ee|r, c f | rdS t | j | j dS )zW
Download the FGVC Aircraft dataset archive and extract it under root.
N)r: r _URLr rQ s r* r9 zFGVCAircraft._downloado s7 F$TY :::::r, c t j | j o#t j | j S rP )r5 r6 existsr8 isdirrQ s r* r: zFGVCAircraft._check_existsw s- w~~do..Q27== 3Q3QQr, )r r r r r r r r r r r r r r r r )r rN )rS rN r rT )r r )r r ) __name__
__module__ __qualname____doc__r[ r r2 rR rY r9 r:
__classcell__)rM s @r* r
r
s < eD
)%),0 '50 0 0 0 0 0 0 d& & & &
; ; ; ;R R R R R R R Rr, r
)
__future__r r5 pathlibr typingr r folderr utilsr r
visionr r
r& r, r* rj s " " " " " " " " " " " " ? ? ? ? ? ? ? ? ! ! ! ! ! !kR kR kR kR kR= kR kR kR kR kRr,