What is the use or purpose of the following lines, which is apparently copying the last column and row of the embedding matrix and repeating it?
clip_embeds = torch.concat((clip_embeds, clip_embeds[:, [-1], :]), dim=1)clip_embeds = torch.concat((clip_embeds, clip_embeds[[-1], :, :]), dim=0)
@Shiva-Gantha Hello, have you figured out the purpose of these 2 lines? I am wondering why where the last column and row of clip feature cloned. Observed same thing while working with LEGAUSSIANS and came here
What is the use or purpose of the following lines, which is apparently copying the last column and row of the embedding matrix and repeating it?
clip_embeds = torch.concat((clip_embeds, clip_embeds[:, [-1], :]), dim=1)
clip_embeds = torch.concat((clip_embeds, clip_embeds[[-1], :, :]), dim=0)
Link to the code: https://github.com/kerrj/lerf/blob/4a13f2074f3f3a162d9b3b9e6c4bbcc21499a7f2/lerf/data/utils/patch_embedding_dataloader.py#L114C9-L115C82