Flowers

class paddle.vision.datasets. Flowers ( data_file=None, label_file=None, setid_file=None, mode='train', transform=None, download=True, backend=None ) [源代码]

Flowers102 数据集的实现。

参数

  • data_file (str,可选) - 数据文件路径,如果 download 参数设置为 Truedata_file 参数可以设置为 None。默认值为 None,默认存放在:~/.cache/paddle/dataset/flowers

  • label_file (str,可选) - 标签文件路径,如果 download 参数设置为 Truelabel_file 参数可以设置为 None。默认值为 None,默认存放在:~/.cache/paddle/dataset/flowers

  • setid_file (str,可选) - 子数据集下标划分文件路径,如果 download 参数设置为 Truesetid_file 参数可以设置为 None。默认值为 None,默认存放在:~/.cache/paddle/dataset/flowers

  • mode (str,可选) - 'train''test' 模式两者之一,默认值为 'train'

  • transform (Callable,可选) - 图片数据的预处理,若为 None 即为不做预处理。默认值为 None

  • download (bool,可选) - 当 data_fileNone 时,该参数决定是否自动下载数据集文件。默认值为 True

  • backend (str,可选) - 指定要返回的图像类型:PIL.Image 或 numpy.ndarray。必须是 {'pil','cv2'} 中的值。如果未设置此选项,将从 paddle.vision.get_image_backend 获得这个值。默认值为 None

返回

Dataset,Flowers 数据集实例。

代码示例

>>> import itertools
>>> import paddle.vision.transforms as T
>>> from paddle.vision.datasets import Flowers

>>> flowers = Flowers()
>>> print(len(flowers))
6149

>>> for i in range(5):  # only show first 5 images
...     img, label = flowers[i]
...     # do something with img and label
...     print(type(img), img.size, label)
...     # <class 'PIL.JpegImagePlugin.JpegImageFile'> (523, 500) [1]

>>> transform = T.Compose(
...     [
...         T.Resize(64),
...         T.ToTensor(),
...         T.Normalize(
...             mean=[0.5, 0.5, 0.5],
...             std=[0.5, 0.5, 0.5],
...             to_rgb=True,
...         ),
...     ]
... )
>>> flowers_test = Flowers(
...     mode="test",
...     transform=transform,  # apply transform to every image
...     backend="cv2",  # use OpenCV as image transform backend
... )
>>> print(len(flowers_test))
1020

>>> for img, label in itertools.islice(iter(flowers_test), 5):  # only show first 5 images
...     # do something with img and label
...     print(type(img), img.shape, label)
...     # <class 'paddle.Tensor'> [3, 64, 96] [1]