point_e/models/transformer.py [297:317]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        cond_drop_prob: float = 0.0,
        frozen_clip: bool = True,
        cache_dir: Optional[str] = None,
        **kwargs,
    ):
        clip = (FrozenImageCLIP if frozen_clip else ImageCLIP)(
            device,
            cache_dir=cache_dir,
        )
        super().__init__(device=device, dtype=dtype, n_ctx=n_ctx + clip.grid_size**2, **kwargs)
        self.n_ctx = n_ctx
        self.clip = clip
        self.clip_embed = nn.Sequential(
            nn.LayerNorm(
                normalized_shape=(self.clip.grid_feature_dim,), device=device, dtype=dtype
            ),
            nn.Linear(self.clip.grid_feature_dim, self.backbone.width, device=device, dtype=dtype),
        )
        self.cond_drop_prob = cond_drop_prob

    def cached_model_kwargs(self, batch_size: int, model_kwargs: Dict[str, Any]) -> Dict[str, Any]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



point_e/models/transformer.py [419:440]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        cond_drop_prob: float = 0.0,
        frozen_clip: bool = True,
        cache_dir: Optional[str] = None,
        **kwargs,
    ):
        clip = (FrozenImageCLIP if frozen_clip else ImageCLIP)(
            device,
            cache_dir=cache_dir,
        )
        super().__init__(device=device, dtype=dtype, n_ctx=n_ctx + clip.grid_size**2, **kwargs)
        self.n_ctx = n_ctx

        self.clip = clip
        self.clip_embed = nn.Sequential(
            nn.LayerNorm(
                normalized_shape=(self.clip.grid_feature_dim,), device=device, dtype=dtype
            ),
            nn.Linear(self.clip.grid_feature_dim, self.backbone.width, device=device, dtype=dtype),
        )
        self.cond_drop_prob = cond_drop_prob

    def cached_model_kwargs(self, batch_size: int, model_kwargs: Dict[str, Any]) -> Dict[str, Any]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -