I am using MultiLabelMarginLoss
loss function. The target values to the loss function are the indices followed by -1.
For example, if the correct label indices are 3 and 4
, the target tensor looks something like this -
target = torch.tensor([3, 4, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1]).to(device)
Is this the correct format for the target?