从python中的一些特殊方法讲到pytorch的官方例子mnist(主要针对pytorch的自定义dataset中的几个特殊函数进行说明)

__str__(self)

  • 该方法中必须有一个return
  • 调用该方法的时机是print对象时
  • return的内容就是print打印的内容

__repr__(self)

  • 该方法与__str__(self)方法一样都是打印时调用的
  • 其中也必须含有return
  • 下面用pytorch官方例子mnist来进行说明:
#每一个自定义的dataset都必须继承类torch.utils.data.Dataset,还必须重写__len__(self)方法和__getitem__(self,index)方法。
#顺便可能会重写__repr__(self)方法,这个不是必须,下面的例子就是自定义dataset类--MNIST类的部分代码:
def __repr__(self):
    fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
    fmt_str += '    Number of datapoints: {}\n'.format(self.__len__())
    tmp = 'train' if self.train is True else 'test'
    fmt_str += '    Split: {}\n'.format(tmp)
    fmt_str += '    Root Location: {}\n'.format(self.root)
    tmp = '    Transforms (if any): '
    fmt_str += '{0}{1}\n'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
    tmp = '    Target Transforms (if any): '
    fmt_str += '{0}{1}'.format(tmp, self.target_transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
    return fmt_str
#当用如下代码实例化MNIST类之后,运用print函数就能调用MNIST类的__repr__(self)函数
d = datasets.MNIST('../data', train=True, download=True,
                   transform=transforms.Compose([
                       transforms.ToTensor(),
                       transforms.Normalize((0.1307,), (0.3081,))]))
print(d)#此时就会调用函数__repr__(self)函数
#输出结果如下:
Dataset MNIST
    Number of datapoints: 60000
    Split: train
    Root Location: ../data
    Transforms (if any): Compose(
                             ToTensor()
                             Normalize(mean=(0.1307,), std=(0.3081,))
                         )
    Target Transforms (if any): None

__getitem__(self,index)

  • 既然说到了__getitem__(self,index),也对其进行讲解。该方法也必须有返回return。
  • 该方法的调用方式是对象名后面加上中括号,中括号中填上索引值。
  • 下面以代码的方式进行展示:
#跟上面代码一样,我们实例化了自定义dataset,然后用索引来取值:
d = datasets.MNIST('../data', train=True, download=True,
                   transform=transforms.Compose([
                       transforms.ToTensor(),
                       transforms.Normalize((0.1307,), (0.3081,))]))
print(d[0])#此时就会调用函数__getitem__(self,index)函数
  • 打印的结果如下,里面包含了一张28×28大小的图像,就是MNIST数据集里面每张图像的大小;还有后面一个一维的tensor就是这张图像的标签索引值。
  • 从打印结果也能够看出,__getitem__(self,index)函数的主要功能就是获取数据和标签,并将其返回。
(tensor([[[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.3860, -0.1951,
          -0.1951, -0.1951,  1.1795,  1.3068,  1.8032, -0.0933,  1.6887,
           2.8215,  2.7197,  1.1923, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.0424,  0.0340,  0.7722,  1.5359,  1.7396,  2.7960,
           2.7960,  2.7960,  2.7960,  2.7960,  2.4396,  1.7650,  2.7960,
           2.6560,  2.0578,  0.3904, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
           0.1995,  2.6051,  2.7960,  2.7960,  2.7960,  2.7960,  2.7960,
           2.7960,  2.7960,  2.7960,  2.7706,  0.7595,  0.6195,  0.6195,
           0.2886,  0.0722, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.1951,  2.3633,  2.7960,  2.7960,  2.7960,  2.7960,  2.7960,
           2.0960,  1.8923,  2.7197,  2.6433, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242,  0.5940,  1.5614,  0.9377,  2.7960,  2.7960,  2.1851,
          -0.2842, -0.4242,  0.1231,  1.5359, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.2460, -0.4115,  1.5359,  2.7960,  0.7213,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242,  1.3450,  2.7960,  1.9942,
          -0.3988, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.2842,  1.9942,  2.7960,
           0.4668, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,  0.0213,  2.6433,
           2.4396,  1.6123,  0.9504, -0.4115, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,  0.6068,
           2.6306,  2.7960,  2.7960,  1.0904, -0.1060, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
           0.1486,  1.9432,  2.7960,  2.7960,  1.4850, -0.0806, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.2206,  0.7595,  2.7833,  2.7960,  1.9560, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242,  2.7451,  2.7960,  2.7451,  0.3904,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
           0.1613,  1.2305,  1.9051,  2.7960,  2.7960,  2.2105, -0.3988,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,  0.0722,  1.4596,
           2.4906,  2.7960,  2.7960,  2.7960,  2.7578,  1.8923, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.1187,  1.0268,  2.3887,  2.7960,
           2.7960,  2.7960,  2.7960,  2.1342,  0.5686, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.1315,  0.4159,  2.2869,  2.7960,  2.7960,  2.7960,
           2.7960,  2.0960,  0.6068, -0.3988, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.1951,
           1.7523,  2.3633,  2.7960,  2.7960,  2.7960,  2.7960,  2.0578,
           0.5940, -0.3097, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242,  0.2758,  1.7650,  2.4524,
           2.7960,  2.7960,  2.7960,  2.7960,  2.6815,  1.2686, -0.2842,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242,  1.3068,  2.7960,  2.7960,
           2.7960,  2.2742,  1.2941,  1.2559, -0.2206, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
         [-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
          -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242]]]), tensor(5))

你可能感兴趣的:(pytorch,python)