Class CAM

monai/visualize/class_activation_maps.py:218–316

Compute class activation map from the last fully-connected layers before the spatial pooling. This implementation is based on: Zhou et al., Learning Deep Features for Discriminative Localization. CVPR '16, https://arxiv.org/abs/1512.04150 Examples .. code-block::

class CAM(CAMBase):
    """
    Compute class activation map from the last fully-connected layers before the spatial pooling.
    This implementation is based on:

        Zhou et al., Learning Deep Features for Discriminative Localization. CVPR '16,
        https://arxiv.org/abs/1512.04150

    Examples

    .. code-block:: python

        import torch

        # densenet 2d
        from monai.networks.nets import DenseNet121
        from monai.visualize import CAM

        model_2d = DenseNet121(spatial_dims=2, in_channels=1, out_channels=3)
        cam = CAM(nn_module=model_2d, target_layers="class_layers.relu", fc_layers="class_layers.out")
        result = cam(x=torch.rand((1, 1, 48, 64)))

        # resnet 2d
        from monai.networks.nets import seresnet50
        from monai.visualize import CAM

        model_2d = seresnet50(spatial_dims=2, in_channels=3, num_classes=4)
        cam = CAM(nn_module=model_2d, target_layers="layer4", fc_layers="last_linear")
        result = cam(x=torch.rand((2, 3, 48, 64)))

    N.B.: To help select the target layer, it may be useful to list all layers:

    .. code-block:: python

        for name, _ in model.named_modules(): print(name)

    See Also:

        - :py:class:`monai.visualize.class_activation_maps.GradCAM`

    """

    def __init__(
        self,
        nn_module: nn.Module,
        target_layers: str,
        fc_layers: str | Callable = "fc",
        upsampler: Callable = default_upsampler,
        postprocessing: Callable = default_normalizer,
    ) -> None:
        """
        Args:
            nn_module: the model to be visualized
            target_layers: name of the model layer to generate the feature map.
            fc_layers: a string or a callable used to get fully-connected weights to compute activation map
                from the target_layers (without pooling).  and evaluate it at every spatial location.
            upsampler: An upsampling method to upsample the output image. Default is
                N dimensional linear (bilinear, trilinear, etc.) depending on num spatial