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

2 votes126 views3 answers
How to loop over month name in python
Python
0 vote126 views1 answer
Old Handler API is deprecated - see https://git.io/fxJuV for details
Python
4 votes134 views6 answers
Online python converter
Python
27 votes123 views2 answers
Python null
Python
0 vote123 views1 answer
Pandas dataframe any along row
Python
0 vote137 views1 answer
Fibonacci in list python
Python
0 vote163 views1 answer
NameError Traceback (most recent call last) <ipython-input-36-28457fcc3f62> in <module> ----> 1 plt.bar(freqs.index, freqs.values, color = "green") 2 plt.show() NameError: name 'freqs' i
Python
0 vote170 views1 answer
Transition from python 2 to 3 terminal
Python
1 vote130 views2 answers
Data series to datetime
Python
0 vote162 views1 answer
Pass context data with templateview in django
Python Django