DiZ( d dl Z d dlZd dlmZ d dlmZ d dlmZmZm Z m
Z
d dl m Z ddl
mZmZmZ ddlmZ G d d
e Zy) N)
namedtuple)Path)AnyCallableOptionalUnion)Image )extract_archiveiterable_to_strverify_str_arg)
VisionDatasetc e Zd ZdZ edg d Zg eddddddd d
ed d ddddd d
ed
dddddd d
eddddddd d
eddddddd d
eddddddd d eddddddd d eddddd ddd ed d d dd ddd ed d!ddd dd d" ed#d$ddd dd d% ed&d'dd(dddd) ed*d+dd(dddd, ed-d.dd(dddd/ ed0d1dd(ddd d2 ed3d4dd(ddd d5 ed6d7dd(ddd d8 ed9d:dd;dddd< ed=d>dd;ddd d< ed?d@dd;ddddA edBdCdd;ddddD edEdFd dGddddH edIdJd!dGddddK edLdMd$dLddddN edOdPd'dQdd ddR edSdTd+dQdd ddU edVdWd.dXdd ddY edZd[d1dXdd dd\ ed]d^d4dXdd dd_ ed`daddXdd d db edcddddXdd d de edfdgd7dXdd ddh edidjd:dXdd ddk edldmd>dXdd ddn edodpdpdXddd dY Z ddreee f dsedteduee
e ef dve e dwe e dxe e dydqf fdz
Z
d{edyeeef fd|Zdyefd}Zdyefd~Zdedyeeef fdZdteduedyefdZ xZS )
Cityscapesaw `Cityscapes `_ Dataset.
Args:
root (str or ``pathlib.Path``): Root directory of dataset where directory ``leftImg8bit``
and ``gtFine`` or ``gtCoarse`` are located.
split (string, optional): The image split to use, ``train``, ``test`` or ``val`` if mode="fine"
otherwise ``train``, ``train_extra`` or ``val``
mode (string, optional): The quality mode to use, ``fine`` or ``coarse``
target_type (string or list, optional): Type of target to use, ``instance``, ``semantic``, ``polygon``
or ``color``. Can also be a list to output a tuple with all specified target types.
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.
transforms (callable, optional): A function/transform that takes input sample and its target as entry
and returns a transformed version.
Examples:
Get semantic segmentation target
.. code-block:: python
dataset = Cityscapes('./data/cityscapes', split='train', mode='fine',
target_type='semantic')
img, smnt = dataset[0]
Get multiple targets
.. code-block:: python
dataset = Cityscapes('./data/cityscapes', split='train', mode='fine',
target_type=['instance', 'color', 'polygon'])
img, (inst, col, poly) = dataset[0]
Validate on the "coarse" set
.. code-block:: python
dataset = Cityscapes('./data/cityscapes', split='val', mode='coarse',
target_type='semantic')
img, smnt = dataset[0]
CityscapesClass)nameidtrain_idcategory category_id
has_instancesignore_in_evalcolor unlabeledr voidFT)r r r z ego vehicler
zrectification border z
out of roi static dynamic )o J r ground )Q r r' road flat) @ r+ sidewalk ) # parking ) z
rail track
) building construction)F r> r> wall )f rA fence
) rF z
guard rail ) rH bridge )r9 d rL tunnel )r9 x Z pole object)rF rF rF polegroup z
traffic light )r4 r5 z traffic sign ) rY r
vegetation nature)k r0 terrain ) ra sky )r> rH person human)rY rX < rider )r r r car vehicle)r r r^ truck )r r r> bus )r ri rL caravan )r r rP trailerrW )r r n train )r P rL
motorcycle )r r r8 bicycle! )w r< r{ z
license plateNrootsplitmode target_type transformtarget_transform
transformsreturnc
t | |||| |dk( rdnd| _ t j j | j d| | _ t j j | j | j | | _ || _ || _
g | _ g | _ t |dd |dk( rd}nd}d } | j ||t | } t |d
|| t! |t" s|g| _ | j D
cg c] }
t |
d d c}
t j j% | j r*t j j% | j s_|d
k( r+t j j | j d } n*t j j | j d } | j dk( r8t j j | j | j d } nF| j dk( r7t j j | j | j d } t j j' | rNt j j' r/t) | | j t) | | j n t+ d t j, | j D ]E }
t j j | j |
}t j j | j |
}t j, | D ] }g }| j D ]o }dj |j d d | j/ | j | }|j1 t j j || q | j j1 t j j || | j j1 | H y c c}
w )NfinegtFinegtCoarse leftImg8bitr )r coarse)rw testval)rw train_extrar zOUnknown value '{}' for argument split if mode is '{}'. Valid values are {{{}}}.r r )instancesemanticpolygonr r zleftImg8bit_trainextra.zipz leftImg8bit_trainvaltest.zipz_trainvaltest.zipz.zip) from_pathto_pathzDataset not found or incomplete. Please make sure all required folders for the specified "split" and "mode" are inside the "root" directoryz{}_{} _leftImg8bitr )super__init__r ospathjoinr
images_dir targets_dirr r imagestargetsr
formatr
isinstancelistisdirisfiler RuntimeErrorlistdir_get_target_suffixappend)selfr r r r r r r valid_modesmsgvalue
image_dir_ziptarget_dir_zipcityimg_dir
target_dir file_name target_typest target_name __class__s a/var/www/pod-logistic/pod-ai/venv/lib/python3.12/site-packages/torchvision/datasets/cityscapes.pyr zCityscapes.__init__i s+ z96FG $HJ '',,tyy-G 77<< 499eD&
tV%78 6>2K9K_jjok&BCug{C8+t, +}D ))
5-1] ^
ww}}T__-RWW]]4CSCS5T
% " TYY8T U
" TYY8V W
yyH$!# diiDII;FW9X!Yj(!# diiDII;d9K!Lww~~m, 1O -K .$))L"T
JJt/ 2Dggll4??D9G d&6&6=J ZZ 0
2 ! )) OA")..!7:D* *r )rw r r NNN)__name__
__module__ __qualname____doc__r r classesr strr r r r r intr r r r r dictr r
__classcell__)r s @r r r
s -` !iO
$ QVQtYO$
q#vq%yQ$ .35$PYZ$ afaiP $
!S&!UD)L $ 1c61eT<P
$ !S&!UD+N$ 1fa~N$
Aq&!UE>R$ 1c61eT?S$ b#vq%W$
B>1eULY$ A~q%X$ Q5% Y $ b#~q%_ $ "c>1eT?[!$" "c>1eT>Z#$$ AxE5/R%$& Rh5$X'$( Q!UE>Z)$* AxE5-X+$, b!Xq%W-$. 2q(Aue_U/$0 r2ua~N1$2 "b'1dE=Q3$4 R!T5+N5$6 r2y!T5+N7$8 RAtUJO9$: r2y!T5,O;$< 2sIq$jQ=$> 2sIq$kR?$@ RAtULQA$B b"iD%UC$D 2r9aumTE$F RAudKXG$GR -7(,/3)-D2CI D2 D2 D2
49c>* D2 H%
D2 #8,D2 X&D2
D2L sCx 6 8C 8s tCH~
+s + + +r r )r r collectionsr pathlibr typingr r r r PILr utilsr r r
visionr r r r r r s1 " 1 1 C C !Q+ Q+r