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

-1 vote348 views2 answers
Sum of all nan values pandas
Python
10 votes306 views1 answer
Dataframe copy
Python
0 vote352 views1 answer
Use ipython magic in script
Python
8 votes316 views2 answers
Python get base directory
Python
3 votes299 views3 answers
Django.db.utils.OperationalError: no such table:
Python
1 vote332 views1 answer
Flask get value of radio button
Python
1 vote324 views1 answer
Passing Functions Around python
Python
5 votes301 views1 answer
How to print for loop in same line in python
Python
0 vote319 views1 answer
Python >>> import this
Python
3 votes319 views2 answers
Return df.iloc[1:]
Python