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

62 votes150 views4 answers
Shuffle list
Python
0 vote166 views2 answers
Scikit learn to identify highly correlated features
Python
0 vote144 views1 answer
My Skile
Python
15 votes151 views10 answers
Hello world
Python
1 vote149 views1 answer
Spacy matcher syntax
Python
8 votes163 views4 answers
Zip a directory in python
Python
0 vote154 views2 answers
Tensorflow conv2d operation
Python
4 votes154 views2 answers
Freq count in python
Python
0 vote148 views1 answer
How to make an entire dataframe show in jupyter
Python
16 votes162 views2 answers
Choice random python
Python