Concat image datasets with different size and number of channels

#1

Good evening everyone,

I got a problem with loading multiple datasets and did not find a solution so far.
For loading multiple datasets into one dataloader I can use the ConcatDataset class, but how do I concatenate e.g. CIFAR10 and MNIST. For this I would have CIFAR10 to resize and convert to grayscale without applying the transformations to MNIST.

Any ideas on how to do that?

#2

You could specify the transformations for each dataset.
This code should work:

mnist = datasets.MNIST(
    root='/home/ptrblck/python/data',
    download=False,
    transform=transforms.Compose([
        transforms.ToTensor()
    ])
)

cifar = datasets.CIFAR10(
    root='/home/ptrblck/python/data',
    download=False,
    transform=transforms.Compose([
        transforms.Grayscale(),
        transforms.Resize(28),
        transforms.ToTensor()
    ])
)

dataset = ConcatDataset((mnist, cifar))

As you can see transforms.Resize and transforms.Grayscale was only applied for the CIFAR10 dataset.

#3

Oh yes of course, I am really a blockhead. :grin:
Thanks!

#4

Can you concatenate the targets using this approach? If not, how do we go about it?

#5

ConcatDataset will concatenate all passed Datasets keeping their samples and targets.

How does ConcatDataset work?