timm/models/mobilenetv3.py [179:221]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.num_classes = num_classes
        # NOTE: cannot meaningfully change pooling of efficient head after creation
        self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
        self.flatten = nn.Flatten(1) if global_pool else nn.Identity()  # don't flatten if pooling disabled
        self.classifier = Linear(self.head_hidden_size, num_classes) if num_classes > 0 else nn.Identity()

    def forward_intermediates(
            self,
            x: torch.Tensor,
            indices: Optional[Union[int, List[int]]] = None,
            norm: bool = False,
            stop_early: bool = False,
            output_fmt: str = 'NCHW',
            intermediates_only: bool = False,
            extra_blocks: bool = False,
    ) -> Union[List[torch.Tensor], Tuple[torch.Tensor, List[torch.Tensor]]]:
        """ Forward features that returns intermediates.

        Args:
            x: Input image tensor
            indices: Take last n blocks if int, all if None, select matching indices if sequence
            norm: Apply norm layer to compatible intermediates
            stop_early: Stop iterating over blocks when last desired intermediate hit
            output_fmt: Shape of intermediate feature outputs
            intermediates_only: Only return intermediate features
            extra_blocks: Include outputs of all blocks and head conv in output, does not align with feature_info
        Returns:

        """
        assert output_fmt in ('NCHW',), 'Output shape must be NCHW.'
        if stop_early:
            assert intermediates_only, 'Must use intermediates_only for early stopping.'
        intermediates = []
        if extra_blocks:
            take_indices, max_index = feature_take_indices(len(self.blocks) + 1, indices)
        else:
            take_indices, max_index = feature_take_indices(len(self.stage_ends), indices)
            take_indices = [self.stage_ends[i] for i in take_indices]
            max_index = self.stage_ends[max_index]

        # forward pass
        feat_idx = 0  # stem is index 0
        x = self.conv_stem(x)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



timm/models/mobilenetv5.py [257:303]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.num_classes = num_classes
        # NOTE: cannot meaningfully change pooling of efficient head after creation
        self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
        self.flatten = nn.Flatten(1) if global_pool else nn.Identity()  # don't flatten if pooling disabled
        self.classifier = Linear(self.head_hidden_size, num_classes) if num_classes > 0 else nn.Identity()

    def forward_intermediates(
            self,
            x: torch.Tensor,
            indices: Optional[Union[int, List[int]]] = None,
            norm: bool = False,
            stop_early: bool = False,
            output_fmt: str = 'NCHW',
            intermediates_only: bool = False,
            extra_blocks: bool = False,
    ) -> Union[List[torch.Tensor], Tuple[torch.Tensor, List[torch.Tensor]]]:
        """ Forward features that returns intermediates.

        Args:
            x: Input image tensor
            indices: Take last n blocks if int, all if None, select matching indices if sequence
            norm: Apply norm layer to compatible intermediates
            stop_early: Stop iterating over blocks when last desired intermediate hit
            output_fmt: Shape of intermediate feature outputs
            intermediates_only: Only return intermediate features
            extra_blocks: Include outputs of all blocks and head conv in output, does not align with feature_info
        Returns:

        """
        assert output_fmt in ('NCHW',), 'Output shape must be NCHW.'
        if stop_early:
            assert intermediates_only, 'Must use intermediates_only for early stopping.'
        intermediates = []
        if extra_blocks:
            take_indices, max_index = feature_take_indices(len(self.blocks) + 1, indices)
        else:
            take_indices, max_index = feature_take_indices(len(self.stage_ends), indices)
            take_indices = [self.stage_ends[i] for i in take_indices]
            max_index = self.stage_ends[max_index]

        # FIXME MFSA and forward_intermediates overlap, they both take indices from specific features
        # When a user wants to grab specific feature maps for a downstream task AND have the msfa output
        # what should we do? Accumulate two intermediates? One for msfa and one for take_indices?

        # forward pass
        feat_idx = 0  # stem is index 0
        x = self.conv_stem(x)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -