13518219792
这篇文章给大家分享的是有关Pytorch如何实现数据加载与数据预处理的内容。小编觉得挺实用的，因此分享给大家做个参考，一起跟随小编过来看看吧。
数据加载分为加载torchvision.datasets中的数据集以及加载自己使用的数据集两种情况。
torchvision.datasets中的数据集
torchvision.datasets中自带MNIST，Imagenet-12，CIFAR等数据集，所有的数据集都是torch.utils.data.Dataset的子类，都包含 _ _ len _ （获取数据集长度）和 _ getItem _ _ （获取数据集中每一项）两个子方法。
Dataset源码如上，可以看到其中包含了两个没有实现的子方法，之后所有的Dataet类都继承该类，并根据数据情况定制这两个子方法的具体实现。
因此当我们需要加载自己的数据集的时候也可以借鉴这种方法，只需要继承torch.utils.data.Dataset类并重写 init ,len,以及getitem这三个方法即可。这样组着的类可以直接作为参数传入到torch.util.data.DataLoader中去。
以CIFAR10为例 源码：
class torchvision.datasets.CIFAR10(root, train=True, transform=None, target_transform=None, download=False)
root (string) – Root directory of dataset where directory cifar-10-batches-py exists or will be saved to if download is set to True. train (bool, optional) – If True, creates dataset from training set, otherwise creates from test set. transform (callable, optional) – A function/transform that takes in an PIL image and returns a transformed version. E.g, transforms.RandomCrop target_transform (callable, optional) – A function/transform that takes in the target and transforms it. download (bool, optional) – If true, downloads the dataset from the internet and puts it in root directory. If dataset is already downloaded, it is not downloaded again.
加载自己的数据集
对于torchvision.datasets中有两个不同的类，分别为DatasetFolder和ImageFolder,ImageFolder是继承自DatasetFolder。
下面我们通过源码来看一看folder文件中DatasetFolder和ImageFolder分别做了些什么
import torch.utils.data as data
from PIL import Image
import os
import os.path
def has_file_allowed_extension(filename, extensions): //检查输入是否是规定的扩展名
"""Checks if a file is an allowed extension.
Args:
filename (string): path to a file
Returns:
bool: True if the filename ends with a known image extension
"""
filename_lower = filename.lower()
return any(filename_lower.endswith(ext) for ext in extensions)
def find_classes(dir):
classes = [d for d in os.listdir(dir) if os.path.isdir(os.path.join(dir, d))] //获取root目录下所有的文件夹名称
classes.sort()
class_to_idx = {classes[i]: i for i in range(len(classes))} //生成类别名称与类别id的对应Dictionary
return classes, class_to_idx
def make_dataset(dir, class_to_idx, extensions):
images = []
dir = os.path.expanduser(dir)// 将~和~user转化为用户目录，对参数中出现~进行处理
for target in sorted(os.listdir(dir)):
d = os.path.join(dir, target)
if not os.path.isdir(d):
continue
for root, _, fnames in sorted(os.walk(d)): //os.work包含三个部分，root代表该目录路径 _代表该路径下的文件夹名称集合，fnames代表该路径下的文件名称集合
for fname in sorted(fnames):
if has_file_allowed_extension(fname, extensions):
path = os.path.join(root, fname)
item = (path, class_to_idx[target])
images.append(item) //生成（训练样本图像目录，训练样本所属类别）的元组
return images //返回上述元组的列表
class DatasetFolder(data.Dataset):
"""A generic data loader where the samples are arranged in this way: ::
root/class_x/xxx.ext
root/class_x/xxy.ext
root/class_x/xxz.ext
root/class_y/123.ext
root/class_y/nsdf3.ext
root/class_y/asd932_.ext
Args:
root (string): Root directory path.
loader (callable): A function to load a sample given its path.
extensions (list[string]): A list of allowed extensions.
transform (callable, optional): A function/transform that takes in
a sample and returns a transformed version.
E.g, ``transforms.RandomCrop`` for images.
target_transform (callable, optional): A function/transform that takes
in the target and transforms it.
Attributes:
classes (list): List of the class names.
class_to_idx (dict): Dict with items (class_name, class_index).
samples (list): List of (sample path, class_index) tuples
"""
def __init__(self, root, loader, extensions, transform=None, target_transform=None):
classes, class_to_idx = find_classes(root)
samples = make_dataset(root, class_to_idx, extensions)
if len(samples) == 0:
raise(RuntimeError("Found 0 files in subfolders of: " + root + "\n"
"Supported extensions are: " + ",".join(extensions)))
self.root = root
self.loader = loader
self.extensions = extensions
self.classes = classes
self.class_to_idx = class_to_idx
self.samples = samples
self.transform = transform
self.target_transform = target_transform
def __getitem__(self, index):
"""
根据index获取sample 返回值为（sample，target）元组，同时如果该类输入参数中有transform和target_transform，torchvision.transforms类型的参数时，将获取的元组分别执行transform和target_transform中的数据转换方法。
Args:
index (int): Index
Returns:
tuple: (sample, target) where target is class_index of the target class.
"""
path, target = self.samples[index]
sample = self.loader(path)
if self.transform is not None:
sample = self.transform(sample)
if self.target_transform is not None:
target = self.target_transform(target)
return sample, target
def __len__(self):
return len(self.samples)
def __repr__(self): //定义输出对象格式 其中和__str__的区别是__repr__无论是print输出还是直接输出对象自身 都是以定义的格式进行输出，而__str__ 只有在print输出的时候会是以定义的格式进行输出
fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
fmt_str += ' Number of datapoints: {}\n'.format(self.__len__())
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
IMG_EXTENSIONS = ['.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif']
def pil_loader(path):
# open path as file to avoid ResourceWarning (https://github.com/python-pillow/Pillow/issues/835)
with open(path, 'rb') as f:
img = Image.open(f)
return img.convert('RGB')
def accimage_loader(path):
import accimage
try:
return accimage.Image(path)
except IOError:
# Potentially a decoding problem, fall back to PIL.Image
return pil_loader(path)
def default_loader(path):
from torchvision import get_image_backend
if get_image_backend() == 'accimage':
return accimage_loader(path)
else:
return pil_loader(path)
class ImageFolder(DatasetFolder):
"""A generic data loader where the images are arranged in this way: ::
root/dog/xxx.png
root/dog/xxy.png
root/dog/xxz.png
root/cat/123.png
root/cat/nsdf3.png
root/cat/asd932_.png
Args:
root (string): Root directory path.
transform (callable, optional): A function/transform that takes in an PIL image
and returns a transformed version. E.g, ``transforms.RandomCrop``
target_transform (callable, optional): A function/transform that takes in the
target and transforms it.
loader (callable, optional): A function to load an image given its path.
Attributes:
classes (list): List of the class names.
class_to_idx (dict): Dict with items (class_name, class_index).
imgs (list): List of (image path, class_index) tuples
"""
def __init__(self, root, transform=None, target_transform=None,
loader=default_loader):
super(ImageFolder, self).__init__(root, loader, IMG_EXTENSIONS,
transform=transform,
target_transform=target_transform)
self.imgs = self.samples如果自己所要加载的数据组织形式如下
root/dog/xxx.png root/dog/xxy.png root/dog/xxz.png root/cat/123.png root/cat/nsdf3.png root/cat/asd932_.png
即不同类别的训练数据分别存储在不同的文件夹中，这些文件夹都在root（即形如 D:/animals 或者 /usr/animals ）路径下
