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

0 vote343 views1 answer
Redirect stdout to variable python
Python
8 votes340 views2 answers
Pandas lambda if else
Python
1 vote362 views2 answers
One hot encoder python
Python
0 vote353 views1 answer
Counting combinations python
Python
0 vote349 views2 answers
Flask heroku
Python
0 vote399 views1 answer
How do you say not equal to python
Python
1 vote388 views2 answers
Incognito selenium
Python
0 vote395 views1 answer
Autopytoexe
Python
0 vote339 views1 answer
Add values to add value in a matplotlib image
Python
11 votes374 views3 answers
Discord rich presence python
Python