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

16 votes174 views5 answers
Pandas groupby aggregate multiple columns
Python
0 vote161 views1 answer
Python join tuple integer to string
Python
0 vote168 views1 answer
User passes test django
Python
2 votes170 views1 answer
How to autosave in python
Python
2 votes176 views1 answer
Python read excel set index
Python
8 votes192 views3 answers
Max value pandas
Python
0 vote181 views1 answer
Pte or Pvt
Python
0 vote200 views1 answer
Delete multiple dataframes at once in python
Python
0 vote232 views2 answers
Radix sort python
Python
3 votes170 views1 answer
Pytz timezone list
Python