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

9 votes278 views3 answers
Create qr code python
Python
2 votes321 views2 answers
Pandas divide one column by another
Python
0 vote290 views3 answers
Datetime columns only extract date pandas
Python
3 votes275 views1 answer
Python remove non letters from string
Python
3 votes297 views2 answers
How to make python code run faster
Python
2 votes282 views1 answer
What skills do you need to master pvp in minecraft
Python
0 vote315 views1 answer
Python geet second item in generator
Python
13 votes313 views3 answers
Np.hstack in python
Python
102 votes320 views6 answers
Python contains
Python
1 vote285 views1 answer
Google colab power level
Python