conjunto de datos de pytorch

import torch 
import torchvision 
import torchvision.transforms as transforms 
#torchvision La salida del conjunto de datos es una PILImage en el rango [0,1], la convertimos en un tensor en el rango normalizado [-1,1] Tensors. 
transform = transforms.Compose ( 
    [transforms.ToTensor (), 
     transforms.Normalize ((0.5,0.5,0.5), (0.5,0.5,0.5))]) 
trainset = torchvision.datasets.CIFAR10 (root = '. / data' , train = True, download = True, transform = transform) 
trainloader = torch.utils.data.DataLoader (trainset, batch_size = 4, shuffle = True, num_workers = 2) 

testset = torchvision.datasets.CIFAR10 (root = '. / data ', train = False, download = True, transform = transform) 

testloader = torch.utils.data.DataLoader (testset, batch_size = 4, shuffle = False, num_workers = 2)
 
classes = (' plane ',' car ', 'pájaro',
           'ciervo', 'perro', 'rana', 'caballo', 'barco', 'camión') 

import matplotlib.pyplot as plt 
import numpy as np 

def imshow (img): 
    img = img / 2 + 0.5 
    npimg = img .numpy () 
    plt.imshow (np.transpose (npimg, (1,2,0))) 
    plt.show () 
dataiter = iter (trainloader) 
imágenes, etiquetas = dataiter.next () 

imshow (torchvision.utils.make_grid (imágenes)) 

print (''. join ('% 5s'% classes [etiquetas [j]] para j en el rango (4)))