Why CIFAR-10 images are not displayed properly using matplotlib?

Make sure you don't normalize your dataset when you want to display the image.

Example :

The loader...

import torch
from torchvision import datasets, transforms
import matplotlib.pyplot as plt


train_loader = torch.utils.data.DataLoader(
    datasets.CIFAR10('../data', train=True, download=True,
                     transform=transforms.Compose([
                         transforms.RandomHorizontalFlip(),
                         transforms.ToTensor(),
                        #  transforms.Normalize(
                        #      (0.4914, 0.4822, 0.4465), (0.247, 0.243, 0.261))
                     ])),
    batch_size=64, shuffle=True)

The code that shows the image...

img = next(iter(train_loader))[0][0]
plt.imshow(transforms.ToPILImage()(img))

Normalized

Wihtout normalization

Following prints 5X5 grid of random Cifar10 images. It isn't blurry, though not perfect either. Any suggestions welcome.

%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
from six.moves import cPickle 

f = open('data/cifar10/cifar-10-batches-py/data_batch_1', 'rb')
datadict = cPickle.load(f,encoding='latin1')
f.close()
X = datadict["data"] 
Y = datadict['labels']
X = X.reshape(10000, 3, 32, 32).transpose(0,2,3,1).astype("uint8")
Y = np.array(Y)

#Visualizing CIFAR 10
fig, axes1 = plt.subplots(5,5,figsize=(3,3))
for j in range(5):
    for k in range(5):
        i = np.random.choice(range(len(X)))
        axes1[j][k].set_axis_off()
        axes1[j][k].imshow(X[i:i+1][0])