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 vote209 views1 answer
How to open camre aopencv
Python
0 vote233 views1 answer
Shutdown flask server with request
Python Flask
51 votes181 views2 answers
How to search for an item in a list in python
Python
0 vote204 views1 answer
Hide grid imshow
Python
1 vote192 views1 answer
Find nth root of m using python
Python
0 vote201 views1 answer
Save python pptx in colab
Python
0 vote188 views1 answer
How many perfect squared lie between 1 and 400
Python
30 votes183 views4 answers
Python get current hour
Python
0 vote183 views1 answer
Select only object columns pandas
Python
0 vote217 views1 answer
Pandas difference between subsequent lines
Python