shap_e/models/transmitter/channels_encoder.py [726:774]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return views_proj

    def views_to_tensor(self, views: Union[torch.Tensor, List[List[Image.Image]]]) -> torch.Tensor:
        """
        Returns a [batch x num_views x 3 x size x size] tensor in the range [-1, 1].
        """
        if isinstance(views, torch.Tensor):
            return views

        tensor_batch = []
        num_views = len(views[0])
        for inner_list in views:
            assert len(inner_list) == num_views
            inner_batch = []
            for img in inner_list:
                img = img.resize((self.image_size,) * 2).convert("RGB")
                inner_batch.append(
                    torch.from_numpy(np.array(img)).to(device=self.device, dtype=torch.float32)
                    / 127.5
                    - 1
                )
            tensor_batch.append(torch.stack(inner_batch, dim=0))
        return torch.stack(tensor_batch, dim=0).permute(0, 1, 4, 2, 3)

    def depths_to_tensor(
        self, depths: Union[torch.Tensor, List[List[Image.Image]]]
    ) -> torch.Tensor:
        """
        Returns a [batch x num_views x 1 x size x size] tensor in the range [-1, 1].
        """
        if isinstance(depths, torch.Tensor):
            return depths

        tensor_batch = []
        num_views = len(depths[0])
        for inner_list in depths:
            assert len(inner_list) == num_views
            inner_batch = []
            for arr in inner_list:
                tensor = torch.from_numpy(arr).clamp(max=self.max_depth) / self.max_depth
                tensor = tensor * 2 - 1
                tensor = F.interpolate(
                    tensor[None, None],
                    (self.image_size,) * 2,
                    mode="nearest",
                )
                inner_batch.append(tensor.to(device=self.device, dtype=torch.float32))
            tensor_batch.append(torch.cat(inner_batch, dim=0))
        return torch.stack(tensor_batch, dim=0)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



shap_e/models/transmitter/pc_encoder.py [352:400]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return views_proj

    def views_to_tensor(self, views: Union[torch.Tensor, List[List[Image.Image]]]) -> torch.Tensor:
        """
        Returns a [batch x num_views x 3 x size x size] tensor in the range [-1, 1].
        """
        if isinstance(views, torch.Tensor):
            return views

        tensor_batch = []
        num_views = len(views[0])
        for inner_list in views:
            assert len(inner_list) == num_views
            inner_batch = []
            for img in inner_list:
                img = img.resize((self.image_size,) * 2).convert("RGB")
                inner_batch.append(
                    torch.from_numpy(np.array(img)).to(device=self.device, dtype=torch.float32)
                    / 127.5
                    - 1
                )
            tensor_batch.append(torch.stack(inner_batch, dim=0))
        return torch.stack(tensor_batch, dim=0).permute(0, 1, 4, 2, 3)

    def depths_to_tensor(
        self, depths: Union[torch.Tensor, List[List[Image.Image]]]
    ) -> torch.Tensor:
        """
        Returns a [batch x num_views x 1 x size x size] tensor in the range [-1, 1].
        """
        if isinstance(depths, torch.Tensor):
            return depths

        tensor_batch = []
        num_views = len(depths[0])
        for inner_list in depths:
            assert len(inner_list) == num_views
            inner_batch = []
            for arr in inner_list:
                tensor = torch.from_numpy(arr).clamp(max=self.max_depth) / self.max_depth
                tensor = tensor * 2 - 1
                tensor = F.interpolate(
                    tensor[None, None],
                    (self.image_size,) * 2,
                    mode="nearest",
                )
                inner_batch.append(tensor.to(device=self.device, dtype=torch.float32))
            tensor_batch.append(torch.cat(inner_batch, dim=0))
        return torch.stack(tensor_batch, dim=0)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -