timm/models/eva.py [749:784]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if i in take_indices:
                intermediates.append(self.norm(x) if norm else x)

        # process intermediates
        if self.num_prefix_tokens:
            # split prefix (e.g. class, distill) and spatial feature tokens
            prefix_tokens = [y[:, 0:self.num_prefix_tokens] for y in intermediates]
            intermediates = [y[:, self.num_prefix_tokens:] for y in intermediates]
        if reshape:
            # reshape to BCHW output format
            H, W = self.patch_embed.dynamic_feat_size((height, width))
            intermediates = [y.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous() for y in intermediates]
        if not torch.jit.is_scripting() and return_prefix_tokens:
            # return_prefix not support in torchscript due to poor type handling
            intermediates = list(zip(intermediates, prefix_tokens))

        if intermediates_only:
            return intermediates

        x = self.norm(x)

        return x, intermediates

    def prune_intermediate_layers(
            self,
            indices: Union[int, List[int]] = 1,
            prune_norm: bool = False,
            prune_head: bool = True,
    ):
        """ Prune layers not required for specified intermediates.
        """
        take_indices, max_index = feature_take_indices(len(self.blocks), indices)
        self.blocks = self.blocks[:max_index + 1]  # truncate blocks
        if prune_norm:
            self.norm = nn.Identity()
        if prune_head:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



timm/models/vision_transformer_relpos.py [434:470]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if i in take_indices:
                # normalize intermediates with final norm layer if enabled
                intermediates.append(self.norm(x) if norm else x)

        # process intermediates
        if self.num_prefix_tokens:
            # split prefix (e.g. class, distill) and spatial feature tokens
            prefix_tokens = [y[:, 0:self.num_prefix_tokens] for y in intermediates]
            intermediates = [y[:, self.num_prefix_tokens:] for y in intermediates]
        if reshape:
            # reshape to BCHW output format
            H, W = self.patch_embed.dynamic_feat_size((height, width))
            intermediates = [y.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous() for y in intermediates]
        if not torch.jit.is_scripting() and return_prefix_tokens:
            # return_prefix not support in torchscript due to poor type handling
            intermediates = list(zip(intermediates, prefix_tokens))

        if intermediates_only:
            return intermediates

        x = self.norm(x)

        return x, intermediates

    def prune_intermediate_layers(
            self,
            indices: Union[int, List[int]] = 1,
            prune_norm: bool = False,
            prune_head: bool = True,
    ):
        """ Prune layers not required for specified intermediates.
        """
        take_indices, max_index = feature_take_indices(len(self.blocks), indices)
        self.blocks = self.blocks[:max_index + 1]  # truncate blocks
        if prune_norm:
            self.norm = nn.Identity()
        if prune_head:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -