o
+ i @ s d dl mZ d dlZd dlZd dlmZmZmZ d dlZ d dl
m Z d dl Z d dl
mZ d dlmZ erTd dlmZ d dlmZ d dlmZ d d
lmZ ed Zed Zg Zd
Z dZ dZ dZ dZ dZ!ddddZ"G dd dee#d Z$dS ) ) annotationsN)
TYPE_CHECKINGAnyLiteral)Image)_check_exists_and_download)Dataset) DTypeLike)
_Transform )_ImageDataType)cv2piltrainvalidtestz=https://dataset.bj.bcebos.com/voc/VOCtrainval_11-May-2012.tarZ 6cd6e144f989b92b3379bac3b3de84fdz/VOCdevkit/VOC2012/ImageSets/Segmentation/{}.txtz#VOCdevkit/VOC2012/JPEGImages/{}.jpgz*VOCdevkit/VOC2012/SegmentationClass/{}.pngZvoc2012Ztrainvalr val)r r r c @ s~ e Zd ZU dZded< ded< ded< ded < d
ed < d ed
< d#d$ddZdd Zd%d d Zd&d d Zd'd!d"Z dS )(VOC2012a
Implementation of `VOC2012 `_ dataset.
Args:
data_file (str|None, 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|None, 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|None, 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(120)
>>> 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) # type: ignore
... # [3, 281, 500]
... print(type(label), label.shape)
... # (281, 500)
str | None data_file _DatasetModemode_Transform[Any, Any] | None transform
_ImageBackendbackendstrflagr dtypeNr Tdownloadbool_ImageBackend | NonereturnNonec C s | dv s
J d| |d u rtj }|dvr!td| || _t| | _|| _| jd u rB|s9J dt |t
t t || _|| _
| t | _d S )Nr z3mode should be 'train', 'valid' or 'test', but got )r r
z4Expected backend are one of ['pil', 'cv2'], but got z>data_file is not set and downloading automatically is disabled)lowerpaddleZvisionZget_image_backend
ValueErrorr
MODE_FLAG_MAPr r r VOC_URLVOC_MD5 CACHE_DIRr
_load_annoZget_default_dtyper )selfr r r r r r. j/home/app/PaddleOCR-VL-test/.venv_paddleocr/lib/python3.10/site-packages/paddle/vision/datasets/voc2012.py__init__ s,
zVOC2012.__init__c C s i | _ t| j| _| j D ]}|| j |j< qt| j }| j
| j | }g | _ g | _ |D ]"}|
}t|d}t|d}| j | | j | q/d S )Nzutf-8)name2memtarfileopenr data_tar
getmembersnameSET_FILEformatr extractfiledatalabelsstrip DATA_FILEdecode
LABEL_FILEappend)r- ZeleZset_fileZsetsliner: labelr. r. r/ r, s zVOC2012._load_annoidxint'tuple[_ImageDataType, npt.NDArray[Any]]c C s | j | }| j| }| j| j| }| j| j| }tt |}tt |}| j
dkr?t |}t |}| j
d urI|
|}| j
dkrZ|| j|| jfS ||fS )Nr
)r: r; r4 r9 r1 readr r3 ioBytesIOr nparrayr Zastyper )r- rC r Z
label_filer: rB r. r. r/ __getitem__ s
zVOC2012.__getitem__c C s
t | jS N)lenr: r- r. r. r/ __len__ s
zVOC2012.__len__c C s | j r
| j d S d S rL )r4 closerN r. r. r/ __del__ s zVOC2012.__del__)Nr NTN) r r r r r r r r! r r" r# r$ )rC rD r# rE )r# rD )r# r$ )
__name__
__module__ __qualname____doc____annotations__r0 r, rK rO rQ r. r. r. r/ r 6 s$
C '
r )r znpt.NDArray[Any])%
__future__r rG r2 typingr r r numpyrI ZPILr r& Zpaddle.dataset.commonr Z paddle.ior Z numpy.typingZnptZpaddle._typingr Z#paddle.vision.transforms.transformsr
imager r r __all__r) r* r7 r= r? r+ r( tupler r. r. r. r/ s2