shap_e/models/transmitter/multiview_encoder.py [102:116]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        all_views = self.views_to_tensor(batch.views).to(self.device)
        if self.use_depth:
            all_views = torch.cat([all_views, self.depths_to_tensor(batch.depths)], dim=2)
        all_cameras = self.cameras_to_tensor(batch.cameras).to(self.device)

        batch_size, num_views, _, _, _ = all_views.shape

        views_proj = self.patch_emb(
            all_views.reshape([batch_size * num_views, *all_views.shape[2:]])
        )
        views_proj = (
            views_proj.reshape([batch_size, num_views, self.width, -1])
            .permute(0, 1, 3, 2)
            .contiguous()
        )  # [batch_size x num_views x n_patches x width]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



shap_e/models/transmitter/pc_encoder.py [327:341]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        all_views = self.views_to_tensor(batch.views).to(self.device)
        if self.use_depth:
            all_views = torch.cat([all_views, self.depths_to_tensor(batch.depths)], dim=2)
        all_cameras = self.cameras_to_tensor(batch.cameras).to(self.device)

        batch_size, num_views, _, _, _ = all_views.shape

        views_proj = self.patch_emb(
            all_views.reshape([batch_size * num_views, *all_views.shape[2:]])
        )
        views_proj = (
            views_proj.reshape([batch_size, num_views, self.width, -1])
            .permute(0, 1, 3, 2)
            .contiguous()
        )  # [batch_size x num_views x n_patches x width]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -