Pytorch數(shù)據(jù)讀取之Dataset和DataLoader知識(shí)總結(jié)

# 導(dǎo)入需要的包
import torch
import torch.utils.data.dataset as Dataset
import numpy as np
 
# 編造數(shù)據(jù)
Data = np.asarray([[1, 2], [3, 4],[5, 6], [7, 8]])
Label = np.asarray([[0], [1], [0], [2]])
# 數(shù)據(jù)[1,2]，對(duì)應(yīng)的標(biāo)簽是[0]，數(shù)據(jù)[3,4],對(duì)應(yīng)的標(biāo)簽是[1]
 
 
#創(chuàng)建子類(lèi)
class subDataset(Dataset.Dataset):
    #初始化，定義數(shù)據(jù)內(nèi)容和標(biāo)簽
    def __init__(self, Data, Label):
        self.Data = Data
        self.Label = Label
    #返回?cái)?shù)據(jù)集大小
    def __len__(self):
        return len(self.Data)
    #得到數(shù)據(jù)內(nèi)容和標(biāo)簽
    def __getitem__(self, index):
        data = torch.Tensor(self.Data[index])
        label = torch.IntTensor(self.Label[index])
        return data, label
 
# 主函數(shù)
if __name__ == '__main__':
    dataset = subDataset(Data, Label)
    print(dataset)
    print('dataset大小為：', dataset.__len__())
    print(dataset.__getitem__(0))
    print(dataset[0])

#創(chuàng)建子類(lèi)
class subDataset(Dataset.Dataset):

DataLoader(dataset,
           batch_size=1,
           shuffle=False,
           sampler=None,
           batch_sampler=None,
           num_works=0,
           clollate_fn=None,
           pin_memory=False,
           drop_last=False,
           timeout=0,
           worker_init_fn=None,
           multiprocessing_context=None)

import torch
import torch.utils.data.dataset as Dataset
import torch.utils.data.dataloader as DataLoader
import numpy as np
 
Data = np.asarray([[1, 2], [3, 4],[5, 6], [7, 8]])
Label = np.asarray([[0], [1], [0], [2]])
#創(chuàng)建子類(lèi)
class subDataset(Dataset.Dataset):
    #初始化，定義數(shù)據(jù)內(nèi)容和標(biāo)簽
    def __init__(self, Data, Label):
        self.Data = Data
        self.Label = Label
    #返回?cái)?shù)據(jù)集大小
    def __len__(self):
        return len(self.Data)
    #得到數(shù)據(jù)內(nèi)容和標(biāo)簽
    def __getitem__(self, index):
        data = torch.Tensor(self.Data[index])
        label = torch.IntTensor(self.Label[index])
        return data, label
 
if __name__ == '__main__':
    dataset = subDataset(Data, Label)
    print(dataset)
    print('dataset大小為：', dataset.__len__())
    print(dataset.__getitem__(0))
    print(dataset[0])
 
    #創(chuàng)建DataLoader迭代器，相當(dāng)于我們要先定義好前面說(shuō)的Dataset,然后再用Dataloader來(lái)對(duì)數(shù)據(jù)進(jìn)行一些操作，比如是否需要打亂，則shuffle=True,是否需要多個(gè)進(jìn)程讀取數(shù)據(jù)num_workers=4,就是四個(gè)進(jìn)程
 
    dataloader = DataLoader.DataLoader(dataset,batch_size= 2, shuffle = False, num_workers= 4)
    for i, item in enumerate(dataloader): #可以用enumerate來(lái)提取出里面的數(shù)據(jù)
        print('i:', i)
        data, label = item #數(shù)據(jù)是一個(gè)元組
        print('data:', data)
        print('label:', label)