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

14 votes251 views3 answers
How to find highest number in list without using max function python
Python
0 vote231 views1 answer
Pytest temp directory
Python
1 vote177 views1 answer
Python check if dataframe type
Python
14 votes294 views3 answers
ModuleNotFoundError: No module named 'pandas_profiling'
Python
7 votes216 views5 answers
Install discord python
Python
107 votes221 views6 answers
Python do while loop
Python
0 vote213 views1 answer
For lopp python
Python
0 vote178 views1 answer
Most valuable features in pandas model
Python
1 vote227 views1 answer
Python export console output to file
Python
0 vote241 views1 answer
Pd assign index from different df
Python