towhee.models.omnivore.omnivore.omnivore_swinb¶
- towhee.models.omnivore.omnivore.omnivore_swinb(pretrained: bool = True, progress: bool = True, load_heads: bool = True, checkpoint_name: str = 'omnivore_swinB', **kwargs: Any) Module [source]¶
Omnivore model trunk: Swin B patch (2,4,4) window (1,6,7,7) :param pretrained: if True loads weights from model trained on
Imagenet 1k, Kinetics 400, SUN RGBD.
- Parameters:
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:
nn.Module of the omnivore model
- Return type:
model