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

11 votes144 views5 answers
Encryption and decryption in python
Python
0 vote181 views1 answer
Using python-poppler
Python
1 vote196 views1 answer
Python list add if not present
Python
0 vote194 views1 answer
Quick way to find the factor of a number python
Python
0 vote174 views1 answer
Add variable to print python
Python
0 vote183 views1 answer
Python get file ending
Python
6 votes234 views1 answer
Pandas change date format to yyyy-mm-dd
Python
10 votes223 views2 answers
Django delete object
Python Django
0 vote169 views1 answer
Get request failed python 443
Python
0 vote183 views1 answer
Drop portion of string in dataframe python
Python