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

2 votes223 views1 answer
Check if camera is being used python
Python
1 vote260 views1 answer
Python KeyError: 'kivy.garden.graph'
Python
0 vote263 views2 answers
How to give order in boxplot matplotlib
Python
6 votes274 views2 answers
Python calculate derivative of function
Python
3 votes258 views1 answer
Djnagi import model form
Python
19 votes249 views3 answers
Convert a list ['Pythons syntax is easy to learn', 'Pythons syntax is very clear'] to a string using ‘&’.
Python
0 vote248 views1 answer
Encoding int to chr in python and vice versa
Python
0 vote237 views1 answer
Gfrequency listing in pandas
Python
0 vote269 views1 answer
How to check if a cell is empty in openpyxl
Python
0 vote244 views1 answer
Django sign up
Python