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 votes232 views1 answer
Django models distinct
Python
1 vote226 views2 answers
Reverse a list in python using recursion
Python
14 votes233 views6 answers
Python binary search
Python
3 votes227 views2 answers
Python try without except
Python
21 votes269 views5 answers
No module named cv2
Python
0 vote251 views1 answer
Find maximum element in stack
Python
0 vote256 views1 answer
Initial TypedMultipleChoiceField django
Python Django
0 vote251 views1 answer
Kivy on press call python function
Python
8 votes196 views4 answers
Reverse dictionary python
Python
7 votes235 views1 answer
Python for loop with array
Python