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

4 votes165 views4 answers
Virtualenv python2
Python
0 vote167 views1 answer
Python n range num list
Python
0 vote151 views1 answer
How to def a variable in python
Python
1 vote163 views1 answer
Model.predict([x_test]) error
Python
0 vote183 views1 answer
How to make a function repeat itself a specifc amount of times python
Python
0 vote168 views1 answer
Pandas groupby counts
Python
0 vote164 views1 answer
Django creat app return _bootstrap._gcd_import
Python
1 vote164 views2 answers
Python regex get word after string
Python
4 votes178 views4 answers
Printing hello world in python
Python
0 vote204 views2 answers
Update a package with pip in django
Python Django