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 vote114 views1 answer
Comparing values in python
Python
0 vote119 views1 answer
Defaultdict initialize keys
Python
1 vote108 views1 answer
Install docx python
Python
-2 votes123 views2 answers
Django form date picker
Python Django
2 votes110 views1 answer
Replacing spaces in a string python
Python
0 vote154 views1 answer
Dataframe groupby rank by multiple column value
Python
32 votes117 views6 answers
Merge pandas
Python
1 vote140 views6 answers
Python filter function
Python
0 vote120 views1 answer
Check if argv exists python
Python
0 vote115 views1 answer
Saving a copy of rcParams settings.
Python