timm/models/efficientformer.py [429:489]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                nn.init.constant_(m.bias, 0)

    @torch.jit.ignore
    def no_weight_decay(self):
        return {k for k, _ in self.named_parameters() if 'attention_biases' in k}

    @torch.jit.ignore
    def group_matcher(self, coarse=False):
        matcher = dict(
            stem=r'^stem',  # stem and embed
            blocks=[(r'^stages\.(\d+)', None), (r'^norm', (99999,))]
        )
        return matcher

    @torch.jit.ignore
    def set_grad_checkpointing(self, enable=True):
        for s in self.stages:
            s.grad_checkpointing = enable

    @torch.jit.ignore
    def get_classifier(self) -> nn.Module:
        return self.head, self.head_dist

    def reset_classifier(self, num_classes: int, global_pool: Optional[str] = None):
        self.num_classes = num_classes
        if global_pool is not None:
            self.global_pool = global_pool
        self.head = nn.Linear(self.num_features, num_classes) if num_classes > 0 else nn.Identity()
        self.head_dist = nn.Linear(self.num_features, num_classes) if num_classes > 0 else nn.Identity()

    @torch.jit.ignore
    def set_distilled_training(self, enable=True):
        self.distilled_training = enable

    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,
    ) -> 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
        Returns:

        """
        assert output_fmt in ('NCHW',), 'Output shape must be NCHW.'
        intermediates = []
        take_indices, max_index = feature_take_indices(len(self.stages), indices)

        # forward pass
        x = self.stem(x)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



timm/models/efficientformer_v2.py [595:655]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                nn.init.constant_(m.bias, 0)

    @torch.jit.ignore
    def no_weight_decay(self):
        return {k for k, _ in self.named_parameters() if 'attention_biases' in k}

    @torch.jit.ignore
    def group_matcher(self, coarse=False):
        matcher = dict(
            stem=r'^stem',  # stem and embed
            blocks=[(r'^stages\.(\d+)', None), (r'^norm', (99999,))]
        )
        return matcher

    @torch.jit.ignore
    def set_grad_checkpointing(self, enable=True):
        for s in self.stages:
            s.grad_checkpointing = enable

    @torch.jit.ignore
    def get_classifier(self) -> nn.Module:
        return self.head, self.head_dist

    def reset_classifier(self, num_classes: int, global_pool: Optional[str] = None):
        self.num_classes = num_classes
        if global_pool is not None:
            self.global_pool = global_pool
        self.head = nn.Linear(self.num_features, num_classes) if num_classes > 0 else nn.Identity()
        self.head_dist = nn.Linear(self.num_features, num_classes) if num_classes > 0 else nn.Identity()

    @torch.jit.ignore
    def set_distilled_training(self, enable=True):
        self.distilled_training = enable

    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,
    ) -> 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
        Returns:

        """
        assert output_fmt in ('NCHW',), 'Output shape must be NCHW.'
        intermediates = []
        take_indices, max_index = feature_take_indices(len(self.stages), indices)

        # forward pass
        x = self.stem(x)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -