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

23 votes349 views2 answers
Python search list
Python
9 votes323 views2 answers
How to read video in opencv python
Python
0 vote293 views1 answer
Get index of value in list if value meet condition python
Python
0 vote310 views1 answer
Object to string pandas
Python
0 vote296 views1 answer
How to make images in python
Python
0 vote325 views1 answer
Bar chart with x-ticks
Python
6 votes323 views2 answers
How to check if django is installed( in python shell)
Python Django
0 vote302 views1 answer
How to get the current url path in django template
Python
36 votes320 views6 answers
Move file python
Python
1 vote346 views1 answer
Model evaluate function
Python