|j2 d dl mZ d dlmZmZmZ er"d dlmZ d dlm Z d dl
m Z ddl m
Z
mZ ed Zd dlZd dlZd dlZd d lmZ d dlZd d
lmZ d d lmZ g Z G d d
ee d Z G d de Z dS ) ) annotations)
TYPE_CHECKINGAnyLiteralN)
_DTypeLiteral)
_Transform )
_ImageBackend_ImageDataTypetraintest)Image)_check_exists_and_download)Datasetc e Zd ZU dZdZdZedz ZdZedz ZdZ edz Z
d Z ed
z Z d Z
d ed
< ded< ded< ded< ded< ded< ded< ded< d*d+d"Zd,d$Zd-d(Zd.d)ZdS )/MNISTaX
Implementation of `MNIST `_ dataset.
Args:
image_path (str|None, optional): Path to image file, can be set None if
:attr:`download` is True. Default: None, default data path: ~/.cache/paddle/dataset/mnist.
label_path (str|None, optional): Path to label file, can be set None if
:attr:`download` is True. Default: None, default data path: ~/.cache/paddle/dataset/mnist.
mode (str, optional): Either train or test mode. Default 'train'.
transform (Callable|None, optional): Transform to perform on image, None for no transform. Default: None.
download (bool, optional): Download dataset automatically if
:attr:`image_path` :attr:`label_path` is not set. Default: True.
backend (str|None, optional): Specifies which type of image to be returned:
PIL.Image or numpy.ndarray. Should be one of {'pil', 'cv2'}.
If this option is not set, will get backend from :ref:`paddle.vision.get_image_backend `,
default backend is 'pil'. Default: None.
Returns:
:ref:`api_paddle_io_Dataset`. An instance of MNIST dataset.
Examples:
.. code-block:: python
>>> import itertools
>>> import paddle.vision.transforms as T
>>> from paddle.vision.datasets import MNIST
>>> mnist = MNIST()
>>> print(len(mnist))
60000
>>> for i in range(5): # only show first 5 images
... img, label = mnist[i]
... # do something with img and label
... print(type(img), img.size, label)
... # (28, 28) [5]
>>> transform = T.Compose(
... [
... T.ToTensor(),
... T.Normalize(
... mean=[127.5],
... std=[127.5],
... ),
... ]
... )
>>> mnist_test = MNIST(
... mode="test",
... transform=transform, # apply transform to every image
... backend="cv2", # use OpenCV as image transform backend
... )
>>> print(len(mnist_test))
10000
>>> for img, label in itertools.islice(iter(mnist_test), 5): # only show first 5 images
... # do something with img and label
... print(type(img), img.shape, label) # type: ignore
... # [1, 28, 28] [7]
mnistz$https://dataset.bj.bcebos.com/mnist/t10k-images-idx3-ubyte.gz 9fb629c4189551a2d022fa330f9573f3t10k-labels-idx1-ubyte.gz ec29112dd5afa0611ce80d1b7f02629ctrain-images-idx3-ubyte.gz f68b3c2dcbeaaa9fbdd348bbdeb94873train-labels-idx1-ubyte.gz d53e105ee54ea40749a09fcbcd1e9432 _DatasetModemode
str | None
image_path
label_path_Transform[Any, Any] | None transformr
backendr dtypelistlabelsimagesNr
Tdownloadbool_ImageBackend | NonereturnNonec | dv s
J d| | t j }|dvrt d| || _ | | _ || _ | j Q|s
J d |dk r| j n| j }|dk r| j
n| j }t |||| j
| | _ || _ | j [|s
J d | j dk r| j n| j } | j dk r| j n| j }
t || |
| j
| | _ || _ | t j | _ d S )Nr z*mode should be 'train' or 'test', but got )pilcv2z4Expected backend are one of ['pil', 'cv2'], but got z?image_path is not set and downloading automatically is disabledr
z?label_path is not set and downloading automatically is disabled)lowerpaddlevisionget_image_backend
ValueErrorr$ r r TRAIN_IMAGE_URLTEST_IMAGE_URLTRAIN_IMAGE_MD5TEST_IMAGE_MD5r NAMEr! TRAIN_LABEL_URLTEST_LABEL_URLTRAIN_LABEL_MD5TEST_LABEL_MD5r# _parse_datasetget_default_dtyper% ) selfr r! r r# r) r$ image_url image_md5 label_url label_md5s l/lsinfo/ai/hellotax_ai/data_center/backend/venv/lib/python3.11/site-packages/paddle/vision/datasets/mnist.py__init__zMNIST.__init__~ s zz||
? > >
? m5577G . ( ( PwPP
JJLL $ ? "
Q
8 )-$$T=P
)-$$T=P
9Iy$)X DO % ? "
Q
8
9'' $$(
9'' $$(
9Iy$)X DO #
-//
d c g | _ g | _ t j | j d 5 }| }t j | j d 5 }| }d}d}d}t j ||| \ } }
} } |t j | z
}d}
d}t j |||
\ }}|
t j | z
}
||k rn:dt | z dz }t j |||
}|
t j | z
}
||z
}dt || z | z z dz }t j ||| }t j ||| | z f
d }|t j | z
}t | D ]l}| j ||d d f | j t j || g
d mB d d d n # 1 swxY w Y d d d d S # 1 swxY w Y d S )
Nrbr z>IIIIz>IIT>Bfloat32int64)r( r' gzipGzipFiler readr! struct unpack_fromcalcsizestrnpreshapeastyperangeappendarray)rA buffer_size
image_fileimg_buf
label_filelab_buf
step_label
offset_imgmagic_byte_img magic_img image_numrowscols
offset_labmagic_byte_lab magic_lab label_num fmt_labelr'
fmt_images images_tempr( is rF r? zMNIST._parse_dataset s
]4?D
1
1 - Z oo''G t55 +
$//++
")393E"GZ4 40 9dD fon = ==
!&'-'9"GZ( ($ 9 fon = ==
!Y.. #c+&6&6 6 %NN5))E <5 %,,w/// /||DJ'' g)>)>>>rH c * t | j S )N)lenr' )rA s rF __len__z
MNIST.__len__ s 4; rH )NNr
NTN)r r r! r r r r# r" r) r* r$ r+ r, r- )rI )rq rr r, rs )r, rr )__name__
__module__ __qualname____doc__r:
URL_PREFIXr7 r9 r< r> r6 r8 r; r= __annotations__rG r? r{ r~ rH rF r r ) s2 > >@ D7J "==N7N "==N7N #??O8O #??O8O****LLLLLL "&!% $15 (,>0 >0 >0 >0 >0@0 0 0 0d? ? ? ?" rH r )r znpt.NDArray[np.int64]c R e Zd ZdZdZdZedz ZdZedz ZdZ edz Z
d Z ed
z Z d Z
d S )
FashionMNISTa
Implementation of `Fashion-MNIST `_ dataset.
Args:
image_path (str, optional): Path to image file, can be set None if
:attr:`download` is True. Default: None, default data path: ~/.cache/paddle/dataset/fashion-mnist.
label_path (str, optional): Path to label file, can be set None if
:attr:`download` is True. Default: None, default data path: ~/.cache/paddle/dataset/fashion-mnist.
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): Whether to download dataset automatically if
:attr:`image_path` :attr:`label_path` is not set. 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 FashionMNIST dataset.
Examples:
.. code-block:: python
>>> import itertools
>>> import paddle.vision.transforms as T
>>> from paddle.vision.datasets import FashionMNIST
>>> fashion_mnist = FashionMNIST()
>>> print(len(fashion_mnist))
60000
>>> for i in range(5): # only show first 5 images
... img, label = fashion_mnist[i]
... # do something with img and label
... print(type(img), img.size, label)
... # (28, 28) [9]
>>> transform = T.Compose(
... [
... T.ToTensor(),
... T.Normalize(
... mean=[127.5],
... std=[127.5],
... ),
... ]
... )
>>> fashion_mnist_test = FashionMNIST(
... mode="test",
... transform=transform, # apply transform to every image
... backend="cv2", # use OpenCV as image transform backend
... )
>>> print(len(fashion_mnist_test))
10000
>>> for img, label in itertools.islice(iter(fashion_mnist_test), 5): # only show first 5 images
... # do something with img and label
... print(type(img), img.shape, label) # type: ignore
... # [1, 28, 28] [9]
z
fashion-mnistz,https://dataset.bj.bcebos.com/fashion_mnist/r bef4ecab320f06d8554ea6380940ec79r bb300cfdad3c16e7a12a480ee83cd310r 8d4fb7e6c68d591d4c3dfef9ec88bf0dr 25c81989df183df01b3e8a0aad5dffbeN)r r r r r: r r7 r9 r< r> r6 r8 r; r= r rH rF r r se > >@ D?J "==N7N "==N7N #??O8O #??O8OOOrH r )
__future__r typingr r r numpy.typingnptpaddle._typing.dtype_liker #paddle.vision.transforms.transformsr ry r
r r rP rS numpyrW PILr r2 paddle.dataset.commonr paddle.ior __all__tupler r r rH rF r su # " " " " " . . . . . . . . . . , 777777>>>>>>55555555?+L
< < < < < <
Y Y Y Y Y GECD E Y Y Y xJ9 J9 J9 J9 J95 J9 J9 J9 J9 J9rH