Concat dataset

class ConcatDataset(torch.utils.data.Dataset):
    def __init__(self, *datasets):
        self.datasets = datasets

    def __getitem__(self, i):
        return tuple(d[i] for d in self.datasets)

    def __len__(self):
        return min(len(d) for d in self.datasets)

train_loader = torch.utils.data.DataLoader(
             ConcatDataset( # concat
                 datasets.ImageFolder(traindir_A),
                 datasets.ImageFolder(traindir_B)
             ),
             batch_size=args.batch_size, shuffle=True,
             num_workers=args.workers, pin_memory=True)

for i, (input, target) in enumerate(train_loader):
    ...

Source: discuss.pytorch.org

Similar codes

0 vote263 views1 answer
Why we need open ( ) and close ( ) in os
Python
0 vote278 views1 answer
How to get a mock image in django?
Python
31 votes260 views6 answers
Regex to validate email
Python
0 vote293 views1 answer
Log of number python
Python
9 votes270 views6 answers
Dropna pandas
Python
-1 vote274 views1 answer
What does filename = path(file).stem python
Python
0 vote278 views1 answer
Megre pandas in dictionary
Python
0 vote283 views1 answer
Chatbot in python github
Python
-1 vote287 views2 answers
Coin flip numpy
Python
0 vote265 views1 answer
16 bit floating point numpy
Python