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

1 vote122 views1 answer
Pyhton built in sort
Python
0 vote133 views1 answer
Which function is used to write all the characters?
Python
13 votes137 views2 answers
How to append to text file with new line by line in python
Python
0 vote95 views1 answer
Django multiple search fields
Python
2 votes126 views2 answers
Exclude index column pandas
Python
3 votes128 views1 answer
Put text on image python
Python
1 vote156 views1 answer
Is there find_all method in re or regex module in python?
Python
12 votes132 views2 answers
Filtering a list
Python
60 votes135 views6 answers
How to use virtual environment python
Python
0 vote137 views1 answer
Python get all ips in a range
Python