快捷導(dǎo)航

Pytorch DataLoader shuffle驗(yàn)證方式

更新時(shí)間：2021年06月01日 16:35:51 作者：循環(huán)是人遞歸是神

這篇文章主要介紹了Pytorch DataLoader shuffle驗(yàn)證方式，具有很好的參考價(jià)值，希望對(duì)大家有所幫助。如有錯(cuò)誤或未考慮完全的地方，望不吝賜教

shuffle = False時(shí)，不打亂數(shù)據(jù)順序

shuffle = True，隨機(jī)打亂

import numpy as np
import h5py
import torch
from torch.utils.data import DataLoader, Dataset  
h5f = h5py.File('train.h5', 'w');
data1 = np.array([[1,2,3],
               [2,5,6],
              [3,5,6],
              [4,5,6]])
data2 = np.array([[1,1,1],
                   [1,2,6],
                  [1,3,6],
                  [1,4,6]])
h5f.create_dataset(str('data'), data=data1)
h5f.create_dataset(str('label'), data=data2)
class Dataset(Dataset):
    def __init__(self):
        h5f = h5py.File('train.h5', 'r')
        self.data = h5f['data']
        self.label = h5f['label']
    def __getitem__(self, index):
        data = torch.from_numpy(self.data[index])
        label = torch.from_numpy(self.label[index])
        return data, label
 
    def __len__(self):
        assert self.data.shape[0] == self.label.shape[0], "wrong data length"
        return self.data.shape[0] 
 
dataset_train = Dataset()
loader_train = DataLoader(dataset=dataset_train,
                           batch_size=2,
                           shuffle = True)
 
for i, data in enumerate(loader_train):
    train_data, label = data
    print(train_data)

pytorch DataLoader使用細(xì)節(jié)

背景：

我一開(kāi)始是對(duì)數(shù)據(jù)擴(kuò)增這一塊有疑問(wèn), 只看到了數(shù)據(jù)變換(torchvisiom.transforms),但是沒(méi)看到數(shù)據(jù)擴(kuò)增, 后來(lái)搞明白了, 數(shù)據(jù)擴(kuò)增在pytorch指的是torchvisiom.transforms + torch.utils.data.DataLoader+多個(gè)epoch共同作用下完成的,

數(shù)據(jù)變換共有以下內(nèi)容

composed = transforms.Compose([transforms.Resize((448, 448)), #  resize
                               transforms.RandomCrop(300), # random crop
                               transforms.ToTensor(),
                               transforms.Normalize(mean=[0.5, 0.5, 0.5],  # normalize
                                                    std=[0.5, 0.5, 0.5])])

簡(jiǎn)單的數(shù)據(jù)讀取類, 進(jìn)返回PIL格式的image:

class MyDataset(data.Dataset):    
    def __init__(self, labels_file, root_dir, transform=None):
        with open(labels_file) as csvfile:
            self.labels_file = list(csv.reader(csvfile))
        self.root_dir = root_dir
        self.transform = transform
        
    def __len__(self):
        return len(self.labels_file)
    
    def __getitem__(self, idx):
        im_name = os.path.join(root_dir, self.labels_file[idx][0])
        im = Image.open(im_name)
        
        if self.transform:
            im = self.transform(im)
            
        return im

下面是主程序

labels_file = "F:/test_temp/labels.csv"
root_dir = "F:/test_temp"
dataset_transform = MyDataset(labels_file, root_dir, transform=composed)
dataloader = data.DataLoader(dataset_transform, batch_size=1, shuffle=False)
"""原始數(shù)據(jù)集共3張圖片, 以batch_size=1, epoch為2 展示所有圖片(共6張)  """
for eopch in range(2):
    plt.figure(figsize=(6, 6)) 
    for ind, i in enumerate(dataloader):
        a = i[0, :, :, :].numpy().transpose((1, 2, 0))
        plt.subplot(1, 3, ind+1)
        plt.imshow(a)