Class TransformerTemporalModelOutput

animation/modules/attention.py:15–24

The output of [`TransformerTemporalModel`]. Args: sample (`torch.FloatTensor` of shape `(batch_size x num_frames, num_channels, height, width)`): The hidden states output conditioned on `encoder_hidden_states` input.

@dataclass
class TransformerTemporalModelOutput(BaseOutput):
    """
    The output of [`TransformerTemporalModel`].

    Args:
        sample (`torch.FloatTensor` of shape `(batch_size x num_frames, num_channels, height, width)`):
            The hidden states output conditioned on `encoder_hidden_states` input.
    """

    sample: torch.FloatTensor


class TransformerTemporalModel(ModelMixin, ConfigMixin):