Using DataLoader to load two tensors

[blade]

I am trying to divide a graph dataset into multiple batches using DataLoader. My input data is consist of a graph signal of size [B, feature * node] and graph adjacency matrix of size [B, node, node]. I was wondering if there is a way to divide both tensor into batches at once using DataLoader.

[blade]

Found the solution here:

@ptrblck

Here is a small example using just random data:

nb_samples = 100
features = torch.randn(nb_samples, 10)
labels = torch.empty(nb_samples, dtype=torch.long).random_(10)
adjacency = torch.randn(nb_samples, 5)
laplacian = torch.randn(nb_samples, 7)

dataset = TensorDataset(features, labels, adjacency, laplacian)
loader = DataLoader(
    dataset,
    batch_size=2
)

for batch_idx, (x, y, a, l) in enumerate(loader):
    print(x.shape, y.shape, a.shape, l.shape)