src/controlnet_aux/midas/midas/vit.py [104:139]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    )

    gs_old = int(math.sqrt(len(posemb_grid)))

    posemb_grid = posemb_grid.reshape(1, gs_old, gs_old, -1).permute(0, 3, 1, 2)
    posemb_grid = F.interpolate(posemb_grid, size=(gs_h, gs_w), mode="bilinear")
    posemb_grid = posemb_grid.permute(0, 2, 3, 1).reshape(1, gs_h * gs_w, -1)

    posemb = torch.cat([posemb_tok, posemb_grid], dim=1)

    return posemb


def forward_flex(self, x):
    b, c, h, w = x.shape

    pos_embed = self._resize_pos_embed(
        self.pos_embed, h // self.patch_size[1], w // self.patch_size[0]
    )

    B = x.shape[0]

    if hasattr(self.patch_embed, "backbone"):
        x = self.patch_embed.backbone(x)
        if isinstance(x, (list, tuple)):
            x = x[-1]  # last feature if backbone outputs list/tuple of features

    x = self.patch_embed.proj(x).flatten(2).transpose(1, 2)

    if getattr(self, "dist_token", None) is not None:
        cls_tokens = self.cls_token.expand(
            B, -1, -1
        )  # stole cls_tokens impl from Phil Wang, thanks
        dist_token = self.dist_token.expand(B, -1, -1)
        x = torch.cat((cls_tokens, dist_token, x), dim=1)
    else:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/controlnet_aux/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/vit.py [20:55]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    )

    gs_old = int(math.sqrt(len(posemb_grid)))

    posemb_grid = posemb_grid.reshape(1, gs_old, gs_old, -1).permute(0, 3, 1, 2)
    posemb_grid = F.interpolate(posemb_grid, size=(gs_h, gs_w), mode="bilinear")
    posemb_grid = posemb_grid.permute(0, 2, 3, 1).reshape(1, gs_h * gs_w, -1)

    posemb = torch.cat([posemb_tok, posemb_grid], dim=1)

    return posemb


def forward_flex(self, x):
    b, c, h, w = x.shape

    pos_embed = self._resize_pos_embed(
        self.pos_embed, h // self.patch_size[1], w // self.patch_size[0]
    )

    B = x.shape[0]

    if hasattr(self.patch_embed, "backbone"):
        x = self.patch_embed.backbone(x)
        if isinstance(x, (list, tuple)):
            x = x[-1]  # last feature if backbone outputs list/tuple of features

    x = self.patch_embed.proj(x).flatten(2).transpose(1, 2)

    if getattr(self, "dist_token", None) is not None:
        cls_tokens = self.cls_token.expand(
            B, -1, -1
        )  # stole cls_tokens impl from Phil Wang, thanks
        dist_token = self.dist_token.expand(B, -1, -1)
        x = torch.cat((cls_tokens, dist_token, x), dim=1)
    else:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -