INNER CODE UNIT · Python

xi

wenhaochai/StableVideo · app.py:245

                    xi=indices.reshape(-1, 2).cpu().numpy(),
                    method="linear",
                ).reshape(res, res)
                interpolated = torch.from_numpy(interpolated).float()
                interpolated[interpolated.isnan()] = 0.0
                f_atlas[i, :, :, c] = interpolated

        f_atlas = f_atlas.permute(0, 3, 2, 1)
        
        # aggregate via simple median as begining
        agg_atlas, _ = torch.median(f_atlas, dim=0)
        
        if if_net == True:
            #####################################
            #           aggregate net           #
            #####################################
            lr, n_epoch = 1e-3, 500
            agg_net = AGGNet().cuda()

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…