j d dl mZ d dlZd dlmZ d dlmZmZmZm Z m
Z
d dl Z ddl
mZmZ ddlmZ G d d e ZdS )
) annotationsN)Path)AnyCallableOptionalTupleUnion ) download_and_extract_archiveverify_str_arg)
VisionDatasetc T e Zd ZdZdZ dd fd
Zd dZd dZd dZd dZ xZ
S )! FGVCAircrafta `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
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.
zWhttps://www.robots.ox.ac.uk/~vgg/data/fgvc-aircraft/archives/fgvc-aircraft-2013b.tar.gztrainvalvariantNFrootUnion[str, Path]splitstrannotation_level transformOptional[Callable]target_transformdownloadboolreturnNonec
t ||| t |dd | _ t |dd | _ t
j | j d | _ |r|
| st d t
j | j dd d
d d| j }t |d 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 |
d 5 }|D ]} | dd \ } }
| j t
j | | d | j | j |
d d d d S # 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.txtrc 6 g | ]}| S )strip).0lines SC:\Projects\Historical\venv\Lib\site-packages\torchvision/datasets/fgvc_aircraft.py
z)FGVCAircraft.__init__..K 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 append)selfr r r r r r annotation_filefimage_data_folder labels_filer*
image_name
label_name __class__s r+ r3 zFGVCAircraft.__init__+ s EUVVV$UG5YZZ !/ 02W"
"
',,ty2GHH NN !!## ^ \]] ] ',, O )( 3
$
&
/3
'
' 8177Q777DL 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 rR s r+ r: zFGVCAircraft._downloadj s7 F$TY :::::r- c t j | j o#t j | j S rQ )r6 r7 existsr9 isdirrR s r+ r; zFGVCAircraft._check_existsr s- w~~do..Q27== 3Q3QQr- )r r NNF)r r r r r r r r r r r r r r )r rO )rT rO r rU )r r )r r ) __name__
__module__ __qualname____doc__r` r3 rS r^ r: r;
__classcell__)rN s @r+ r r
s 6 eD
)(,/3 .C .C .C .C .C .C .C`& & & &
; ; ; ;R R R R R R R Rr- r )
__future__r r6 pathlibr typingr r r r r PIL.ImagerX utilsr r visionr
r r' r- r+ ro s " " " " " " 8 8 8 8 8 8 8 8 8 8 8 8 8 8 ? ? ? ? ? ? ? ? ! ! ! ! ! !fR fR fR fR fR= fR fR fR fR fRr-