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

0 vote196 views1 answer
Python write error to file
Python
0 vote218 views1 answer
String times python
Python
1 vote198 views2 answers
Python dictionary default value if key doesn't exist
Python
2 votes200 views2 answers
Generate random integer matrix python
Python
7 votes208 views4 answers
Python import timezone
Python
0 vote202 views1 answer
Get the time of 1 minute later in python
Python
5 votes210 views5 answers
Nmap
Python
0 vote217 views1 answer
Rqg3
Python
19 votes206 views4 answers
Install python on ubuntu
Python
0 vote205 views1 answer
Sendgrid django smtp
Python