Why mnist has just 50000 images?

1 
dl_train = DataLoader( torchvision.datasets.CIFAR10('/data/cifar10', download=True, train=True), batch_size=1, drop_last=False, shuffle=False)
print(len(dl_train))

returns just 50.000 should it be 60.000?

2

According to Wikipedia

The MNIST database contains 60,000 training images and 10,000 testing images.

3

Here you go :slight_smile:

1 Like
4

@Hmrishav_Bandyopadhy

Take my full code execute on your end and let me know if you get 60.000

import torchvision
from torch.utils.data import DataLoader, Dataset, TensorDataset
dl_train = DataLoader( torchvision.datasets.CIFAR10('/data2/cifar10', download=True, train=True), batch_size=1, drop_last=False, shuffle=False)
print(len(dl_train))
5

Hi,
You are actually using extracting CIFAR dataset as i mentioned in the previous answer. CIFAR dataset has 50,000 training images and 10,000 testing images.

Use this for MNIST:

import torchvision
from torch.utils.data import DataLoader, Dataset, TensorDataset
dl_train = DataLoader( torchvision.datasets.MNIST(root, download=True, train=True),batch_size=1, drop_last=False, shuffle=False)
print(len(dl_train))
1 Like
6

Thanks @Hmrishav_Bandyopadhy you saved my day.