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

8 votes109 views2 answers
Discord python get member object by id
Python
0 vote112 views1 answer
Python is program running
Python
1 vote112 views1 answer
'charmap' codec can't decode byte 0x98 in position 11354: character maps to <undefined>
Python
2 votes100 views3 answers
Selenium find element by link text python
Python
-1 vote120 views1 answer
Py to flag converter online
Python
0 vote104 views1 answer
DatetimeProperties' object has no attribute 'weekday_name'
Python
-4 votes98 views5 answers
Current django version
Python
2 votes110 views1 answer
Isolate row based on index pandas
Python
1 vote98 views1 answer
Python list add if not present
Python
13 votes106 views4 answers
Python write list to text file
Python