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 vote217 views1 answer
Pandas removing outliers from dataframe
Python
0 vote223 views1 answer
Dataflair python
Python
-1 vote207 views1 answer
Install python module github
Python
0 vote228 views1 answer
Flask python use specified port
Python Flask
0 vote177 views1 answer
Pandas count unique index
Python
0 vote234 views1 answer
Spacy text annotation dict comprehension
Python
91 votes202 views6 answers
Conda create environment python 3
Python
-1 vote211 views2 answers
How to clear combobox tkinter
Python
0 vote227 views1 answer
List exaple in python
Python
1 vote224 views1 answer
Dashes seaborn
Python