segformer model implementation != original arch design

In the segformer paper, the diagram looks like this <img width="1610" height="748" alt="Image" src="https://github.com/user-attachments/assets/69ba4a96-4dc1-4a57-b3f0-b9e442c933c4" /> But in this repo, the [code](https://github.com/qubvel-org/segmentation_models.pytorch/blob/main/segmentation_models_pytorch/decoders/segformer/model.py) is written as below. How come it has encoder name attribute, there's no CNN feature extraction separately in the original design plan? ```python @supports_config_loading def __init__( self, encoder_name: str = "resnet34", encoder_depth: int = 5, encoder_weights: Optional[str] = "imagenet", decoder_segmentation_channels: int = 256, in_channels: int = 3, classes: int = 1, activation: Optional[Union[str, Callable]] = None, upsampling: int = 4, aux_params: Optional[dict] = None, **kwargs: dict[str, Any], ): super().__init__() self.encoder = get_encoder( encoder_name, in_channels=in_channels, depth=encoder_depth, weights=encoder_weights, **kwargs, ) self.decoder = SegformerDecoder( encoder_channels=self.encoder.out_channels, encoder_depth=encoder_depth, segmentation_channels=decoder_segmentation_channels, ) self.segmentation_head = SegmentationHead( in_channels=decoder_segmentation_channels, out_channels=classes, activation=activation, kernel_size=1, upsampling=upsampling, ) if aux_params is not None: self.classification_head = ClassificationHead( in_channels=self.encoder.out_channels[-1], **aux_params ) else: self.classification_head = None self.name = "segformer-{}".format(encoder_name) self.initialize() ````