\;jA d dl Z d dlZd dlZd dlmZ d dlZd dlmZ d dl m
Z
g Z dZ dZ
dZdZd Zd
Zd d d
dZ G d de
Zy) N)Image)_check_exists_and_download)Datasetz=https://dataset.bj.bcebos.com/voc/VOCtrainval_11-May-2012.tar 6cd6e144f989b92b3379bac3b3de84fdz/VOCdevkit/VOC2012/ImageSets/Segmentation/{}.txtz#VOCdevkit/VOC2012/JPEGImages/{}.jpgz*VOCdevkit/VOC2012/SegmentationClass/{}.pngvoc2012trainvaltrainval)r testvalidc : e Zd ZdZ ddZd Zd Zd Zd Zy) VOC2012a
Implementation of `VOC2012 `_ dataset.
Args:
data_file (str, optional): Path to data file, can be set None if
:attr:`download` is True. Default: None, default data path: ~/.cache/paddle/dataset/voc2012.
mode (str, optional): Either train or test mode. Default 'train'.
transform (Callable, optional): Transform to perform on image, None for no transform. Default: None.
download (bool, optional): Download dataset automatically if :attr:`data_file` is None. Default: True.
backend (str, optional): Specifies which type of image to be returned:
PIL.Image or numpy.ndarray. Should be one of {'pil', 'cv2'}.
If this option is not set, will get backend from :ref:`paddle.vision.get_image_backend `,
default backend is 'pil'. Default: None.
Returns:
:ref:`api_paddle_io_Dataset`. An instance of VOC2012 dataset.
Examples:
.. code-block:: python
>>> # doctest: +TIMEOUT(75)
>>> import itertools
>>> import paddle.vision.transforms as T
>>> from paddle.vision.datasets import VOC2012
>>> voc2012 = VOC2012()
>>> print(len(voc2012))
2913
>>> for i in range(5): # only show first 5 images
... img, label = voc2012[i]
... # do something with img and label
... print(type(img), img.size)
... # (500, 281)
... print(type(label), label.size)
... # (500, 281)
>>> transform = T.Compose(
... [
... T.ToTensor(),
... T.Normalize(
... mean=[0.5, 0.5, 0.5],
... std=[0.5, 0.5, 0.5],
... to_rgb=True,
... ),
... ]
... )
>>> voc2012_test = VOC2012(
... mode="test",
... transform=transform, # apply transform to every image
... backend="cv2", # use OpenCV as image transform backend
... )
>>> print(len(voc2012_test))
1464
>>> for img, label in itertools.islice(iter(voc2012_test), 5): # only show first 5 images
... # do something with img and label
... print(type(img), img.shape)
... # [3, 281, 500]
... print(type(label), label.shape)
... # (281, 500)
Nc |j dv s
J d| | t j j }|dvrt d| || _ t |j | _ || _ | j )|sJ d t |t t t | | _ || _
| j t j | _ y )N)r r r z3mode should be 'train', 'valid' or 'test', but got )pilcv2z4Expected backend are one of ['pil', 'cv2'], but got z>data_file is not set and downloading automatically is disabled)lowerpaddlevisionget_image_backend
ValueErrorbackend
MODE_FLAG_MAPflag data_filer VOC_URLVOC_MD5 CACHE_DIR transform
_load_annoget_default_dtypedtype)selfr moder downloadr s gG:\00. PROJECTS\API\Inventory\templateJSON\kerjaOCR\Lib\site-packages\paddle/vision/datasets/voc2012.py__init__zVOC2012.__init__k s zz|
H A G H
? mm557G . ( FwiP
!$**,/ " >> !
PO
P 77GY DN #
--/
c i | _ t j | j | _ | j j D ] }|| j |j < t j | j }| j j | j | }g | _ g | _ |D ] }|j }t j |j d }t j |j d }| j j# | | j j# | y )Nzutf-8)name2memtarfileopenr data_tar
getmembersnameSET_FILEformatr extractfiledatalabelsstrip DATA_FILEdecode
LABEL_FILEappend)r" eleset_filesetsliner2 labels r% r zVOC2012._load_anno s
T^^4
==++-C&)DMM#(( # . ??499-}}(( x)@A D::DHHUOE >> %>>$'D <<5 ;;tzz*ELL,DD DU{r' c , t | j S N)lenr2 r" s r% __len__zVOC2012.__len__ s 499~ r' c R | j r| j j y y rI )r, closerK s r% __del__zVOC2012.__del__ s == MM ! r' )Nr NTN) __name__
__module__ __qualname____doc__r& r rG rL rO r' r% r r ' s4 AJ
%0N&&* "r' r )r@ r* numpyrB PILr r paddle.dataset.commonr paddle.ior __all__r r r/ r5 r7 r r r rT r' r% rZ sY
<
I
, < 1
9
$gF
X"g X"r'