Method compute_map

monai/visualize/class_activation_maps.py:194–206

Compute the actual feature map with input tensor `x`. Args: x: input to `nn_module`. class_idx: index of the class to be visualized. Default to `None` (computing `class_idx` from `argmax`) layer_idx: index of the target layer if there are multipl

(self, x, class_idx=None, layer_idx=-1)

        return self.compute_map(torch.zeros(*input_size, device=device), layer_idx=layer_idx, **kwargs).shape

    def compute_map(self, x, class_idx=None, layer_idx=-1):
        """
        Compute the actual feature map with input tensor `x`.

        Args:
            x: input to `nn_module`.
            class_idx: index of the class to be visualized. Default to `None` (computing `class_idx` from `argmax`)
            layer_idx: index of the target layer if there are multiple target layers. Defaults to -1.

        Returns:
            activation maps (raw outputs without upsampling/post-processing.)
        """
        raise NotImplementedError()

    def _upsample_and_post_process(self, acti_map, x):
        # upsampling and postprocessing