timm/models/efficientvit_mit.py [732:832]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
        self.head_hidden_size = self.head.num_features

    @torch.jit.ignore
    def group_matcher(self, coarse=False):
        matcher = dict(
            stem=r'^stem',
            blocks=r'^stages\.(\d+)' if coarse else [
                (r'^stages\.(\d+).downsample', (0,)),
                (r'^stages\.(\d+)\.\w+\.(\d+)', None),
            ]
        )
        return matcher

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

    @torch.jit.ignore
    def get_classifier(self) -> nn.Module:
        return self.head.classifier[-1]

    def reset_classifier(self, num_classes: int, global_pool: Optional[str] = None):
        self.num_classes = num_classes
        self.head.reset(num_classes, global_pool)

    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)

        if torch.jit.is_scripting() or not stop_early:  # can't slice blocks in torchscript
            stages = self.stages
        else:
            stages = self.stages[:max_index + 1]

        for feat_idx, stage in enumerate(stages):
            if self.grad_checkpointing and not torch.jit.is_scripting():
                x = checkpoint_seq(stages, x)
            else:
                x = stage(x)
            if feat_idx in take_indices:
                intermediates.append(x)

        if intermediates_only:
            return intermediates

        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.stages), indices)
        self.stages = self.stages[:max_index + 1]  # truncate blocks w/ stem as idx 0
        if prune_head:
            self.reset_classifier(0, '')
        return take_indices

    def forward_features(self, x):
        x = self.stem(x)
        if self.grad_checkpointing and not torch.jit.is_scripting():
            x = checkpoint_seq(self.stages, x)
        else:
            x = self.stages(x)
        return x

    def forward_head(self, x, pre_logits: bool = False):
        return self.head(x, pre_logits=pre_logits) if pre_logits else self.head(x)

    def forward(self, x):
        x = self.forward_features(x)
        x = self.forward_head(x)
        return x
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



timm/models/efficientvit_mit.py [889:989]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
        self.head_hidden_size = self.head.num_features

    @torch.jit.ignore
    def group_matcher(self, coarse=False):
        matcher = dict(
            stem=r'^stem',
            blocks=r'^stages\.(\d+)' if coarse else [
                (r'^stages\.(\d+).downsample', (0,)),
                (r'^stages\.(\d+)\.\w+\.(\d+)', None),
            ]
        )
        return matcher

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

    @torch.jit.ignore
    def get_classifier(self) -> nn.Module:
        return self.head.classifier[-1]

    def reset_classifier(self, num_classes: int, global_pool: Optional[str] = None):
        self.num_classes = num_classes
        self.head.reset(num_classes, global_pool)

    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)

        if torch.jit.is_scripting() or not stop_early:  # can't slice blocks in torchscript
            stages = self.stages
        else:
            stages = self.stages[:max_index + 1]

        for feat_idx, stage in enumerate(stages):
            if self.grad_checkpointing and not torch.jit.is_scripting():
                x = checkpoint_seq(stages, x)
            else:
                x = stage(x)
            if feat_idx in take_indices:
                intermediates.append(x)

        if intermediates_only:
            return intermediates

        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.stages), indices)
        self.stages = self.stages[:max_index + 1]  # truncate blocks w/ stem as idx 0
        if prune_head:
            self.reset_classifier(0, '')
        return take_indices

    def forward_features(self, x):
        x = self.stem(x)
        if self.grad_checkpointing and not torch.jit.is_scripting():
            x = checkpoint_seq(self.stages, x)
        else:
            x = self.stages(x)
        return x

    def forward_head(self, x, pre_logits: bool = False):
        return self.head(x, pre_logits=pre_logits) if pre_logits else self.head(x)

    def forward(self, x):
        x = self.forward_features(x)
        x = self.forward_head(x)
        return x
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -