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 vote359 views1 answer
Django round 2 decimal
Python
1 vote343 views2 answers
Perfect number program in python
Python
2 votes370 views2 answers
Get Discord guild members discord.py
Python
0 vote313 views1 answer
Python list of deeper paths
Python
15 votes318 views2 answers
Python randomise between 0 or 1
Python
0 vote367 views1 answer
Label default text value python
Python
0 vote342 views1 answer
Inspect last 5 rows of dataframe
Python
0 vote355 views1 answer
Connectionrefusederror at /accounts/signup/ django allauth
Python Django
3 votes335 views1 answer
Draw a single pixel using pygame
Python
0 vote322 views1 answer
Pandas use map lambda to fillna python
Python