SenticGCNModelOutput

class SenticGCNModelOutput(loss: Optional[torch.Tensor] = None, logits: Optional[torch.Tensor] = None)

Base class for outputs of SenticGCNModel.

Parameters

• loss (torch.Tensor of shape (1,), optional, return when labels is provided) – classification loss, typically cross entropy. Loss function used is dependent on what is specified in SenticGCNConfig.

• logits (torch.Tensor of shape (batch_size, num_classes)) – raw logits for each class. num_classes = 3 by default.