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

10 votes189 views1 answer
How to varify pip is install in python
Python
45 votes204 views6 answers
Array python
Python
68 votes177 views5 answers
Pandas iterate rows
Python
28 votes184 views3 answers
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xa5 in position 10: invalid start byte
Python
2 votes186 views1 answer
Django and react url conflict
Python
0 vote210 views1 answer
Passing array to methods
Python
5 votes203 views2 answers
Print all of dataframe
Python
5 votes185 views1 answer
What is seaborn in python
Python
0 vote202 views1 answer
Python item defined in different definition stackoverflow
Python
0 vote186 views1 answer
Delete nans in df python
Python