Method __init__

monai/networks/nets/efficientnet.py:232–408

EfficientNet based on `Rethinking Model Scaling for Convolutional Neural Networks `_. Adapted from `EfficientNet-PyTorch `_. Args: blocks_args_str: block definitions.

(
        self,
        blocks_args_str: list[str],
        spatial_dims: int = 2,
        in_channels: int = 3,
        num_classes: int = 1000,
        width_coefficient: float = 1.0,
        depth_coefficient: float = 1.0,
        dropout_rate: float = 0.2,
        image_size: int = 224,
        norm: str | tuple = ("batch", {"eps": 1e-3, "momentum": 0.01}),
        drop_connect_rate: float = 0.2,
        depth_divisor: int = 8,
    )

class EfficientNet(nn.Module):

    def __init__(
        self,
        blocks_args_str: list[str],
        spatial_dims: int = 2,
        in_channels: int = 3,
        num_classes: int = 1000,
        width_coefficient: float = 1.0,
        depth_coefficient: float = 1.0,
        dropout_rate: float = 0.2,
        image_size: int = 224,
        norm: str | tuple = ("batch", {"eps": 1e-3, "momentum": 0.01}),
        drop_connect_rate: float = 0.2,
        depth_divisor: int = 8,
    ) -> None:
        """
        EfficientNet based on `Rethinking Model Scaling for Convolutional Neural Networks <https://arxiv.org/pdf/1905.11946.pdf>`_.
        Adapted from `EfficientNet-PyTorch <https://github.com/lukemelas/EfficientNet-PyTorch>`_.

        Args:
            blocks_args_str: block definitions.
            spatial_dims: number of spatial dimensions.
            in_channels: number of input channels.
            num_classes: number of output classes.
            width_coefficient: width multiplier coefficient (w in paper).
            depth_coefficient: depth multiplier coefficient (d in paper).
            dropout_rate: dropout rate for dropout layers.
            image_size: input image resolution.
            norm: feature normalization type and arguments.
            drop_connect_rate: dropconnect rate for drop connection (individual weights) layers.
            depth_divisor: depth divisor for channel rounding.

        """
        super().__init__()

        if spatial_dims not in (1, 2, 3):
            raise ValueError("spatial_dims can only be 1, 2 or 3.")

        # select the type of N-Dimensional layers to use
        # these are based on spatial dims and selected from MONAI factories
        conv_type: type[nn.Conv1d | nn.Conv2d | nn.Conv3d] = Conv["conv", spatial_dims]
        adaptivepool_type: type[nn.AdaptiveAvgPool1d | nn.AdaptiveAvgPool2d | nn.AdaptiveAvgPool3d] = Pool[
            "adaptiveavg", spatial_dims
        ]

        # decode blocks args into arguments for MBConvBlock
        blocks_args = [BlockArgs.from_string(s) for s in blocks_args_str]

        # checks for successful decoding of blocks_args_str
        if not isinstance(blocks_args, list):
            raise ValueError("blocks_args must be a list")

        if blocks_args == []:
            raise ValueError("block_args must be non-empty")

        self._blocks_args = blocks_args
        self.num_classes = num_classes
        self.in_channels = in_channels
        self.drop_connect_rate = drop_connect_rate