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

3 votes131 views2 answers
Discord.py edit messages
Python
30 votes139 views3 answers
Iterating index array python
Python
3 votes177 views1 answer
Remove keys from dict python
Python
0 vote140 views1 answer
Visual Studio Code doesn't stop on Python breakpoint debug
Python
11 votes128 views2 answers
Python index max list
Python
0 vote142 views1 answer
Pyinstaller onefile current working directory
Python
1 vote134 views1 answer
Best Python Free Tutorial
Python
0 vote136 views1 answer
How to go up levels in path python
Python
1 vote164 views1 answer
Jpython
Python
1 vote141 views1 answer
Python get object attribute by string
Python