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 vote303 views1 answer
Program to segregate positive and negative numbers in same list
Python
2 votes336 views2 answers
Cv2 crop image
Python
11 votes269 views6 answers
Pandas distinct
Python
6 votes256 views6 answers
Python ide
Python
0 vote261 views1 answer
IsADirectoryError: [Errno 21] Is a directory: '/'
Python
0 vote273 views1 answer
Onetoone vs foreign key django
Python Django
0 vote254 views1 answer
How to import files from desktop to python
Python
3 votes259 views2 answers
Python list copy
Python
0 vote282 views1 answer
How to predict the output for new data with the model tested already
Python
0 vote291 views2 answers
Import static
Python