简单测试一下pytorch dataloader里的shuffle=True是如何工作的

import sys
import torch
import random
import argparse
import numpy as np
import pandas as pd
import torch.nn as nn
from torch.nn import functional as F
from torch.optim import lr_scheduler
from torchvision import datasets, transforms
from torch.utils.data import TensorDataset, DataLoader, Dataset

class DealDataset(Dataset):
    def __init__(self):
        xy = np.loadtxt(open('./iris.csv','rb'), delimiter=',', dtype=np.float32)
        #data = pd.read_csv("iris.csv",header=None)
        #xy = data.values
        self.x_data = torch.from_numpy(xy[:, 0:-1])
        self.y_data = torch.from_numpy(xy[:, [-1]])
        self.len = xy.shape[0]
    
    def __getitem__(self, index):
        return self.x_data[index], self.y_data[index]

    def __len__(self):
        return self.len
   
dealDataset = DealDataset()

train_loader2 = DataLoader(dataset=dealDataset,
                          batch_size=2,
                          shuffle=True)
#print(dealDataset.x_data)
for i, data in enumerate(train_loader2):
    inputs, labels = data

    #inputs, labels = Variable(inputs), Variable(labels)
    print(inputs)
    #print("epoch：", epoch, "的第" , i, "个inputs", inputs.data.size(), "labels", labels.data.size())

简易数据集 

shuffle之后的结果，每次都是随机打乱，然后分成大小为n的若干个mini-batch.