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

23 votes374 views2 answers
Map function in python
Python
2 votes149 views1 answer
Distance matrix in python
Python
0 vote160 views1 answer
Gematria python
Python
-2 votes147 views1 answer
How To Download Panda3D
Python
140 votes151 views6 answers
Python random integer in range
Python
0 vote137 views1 answer
Import "whitenoise.django" could not be resolved
Python
0 vote157 views1 answer
Keras reshape
Python
0 vote143 views1 answer
La commande pop python
Python
1 vote150 views1 answer
Deleting an object in python
Python
0 vote144 views1 answer
Install pytorch on nvidia jetson nx
Python