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 votes290 views2 answers
Generate random prime number python
Python
6 votes257 views4 answers
Install python3 in ubuntu
Python
0 vote176 views1 answer
Visualizzare csv in pycharm pandas read_csv
Python
0 vote173 views1 answer
Open dicom images python
Python
0 vote157 views1 answer
* pattern by python
Python
0 vote219 views1 answer
Python logging basicConfig+time
Python
0 vote166 views2 answers
How to create a file in a specific location in python
Python
5 votes182 views1 answer
Python read file without newline
Python
2 votes170 views3 answers
How to get an input into a list python
Python
-1 vote186 views1 answer
Python unicode point to utf8 string
Python