models/omnivore_model.py [196:220]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    pretrained: bool = True,
    progress: bool = True,
    load_heads: bool = True,
    **kwargs: Any,
) -> nn.Module:
    r"""
    Omnivore model trunk: Swin S patch (2,4,4) window (8,7,7)

    Args:
        pretrained: if True loads weights from model trained on
            Imagenet 1k, Kinetics 400, SUN RGBD.
        progress: print progress of loading checkpoint
        load_heads: if True, loads the 3 heads, one each for
            image/video/rgbd prediction. If False loads only the
            trunk.
    
    Returns: 
        model: nn.Module of the omnivore model
    """

    # Only specify the non default values
    trunk = SwinTransformer3D(
        pretrained2d=False,
        patch_size=(2, 4, 4),
        embed_dim=96,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



models/omnivore_model.py [241:265]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    pretrained: bool = True,
    progress: bool = True,
    load_heads: bool = True,
    **kwargs: Any,
) -> nn.Module:
    r"""
    Omnivore model trunk: Swin T patch (2,4,4) window (8,7,7)
    
    Args:
        pretrained: if True loads weights from model trained on
            Imagenet 1k, Kinetics 400, SUN RGBD.
        progress: print progress of loading checkpoint
        load_heads: if True, loads the 3 heads, one each for
            image/video/rgbd prediction. If False loads only the
            trunk.
    
    Returns: 
        model: nn.Module of the omnivore model
    """

    # Only specify the non default values
    trunk = SwinTransformer3D(
        pretrained2d=False,
        patch_size=(2, 4, 4),
        embed_dim=96,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -