| # Copyright (c) 2023-2024, Zexin He | |
| # | |
| # Licensed under the Apache License, Version 2.0 (the "License"); | |
| # you may not use this file except in compliance with the License. | |
| # You may obtain a copy of the License at | |
| # | |
| # https://www.apache.org/licenses/LICENSE-2.0 | |
| # | |
| # Unless required by applicable law or agreed to in writing, software | |
| # distributed under the License is distributed on an "AS IS" BASIS, | |
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
| # See the License for the specific language governing permissions and | |
| # limitations under the License. | |
| import torch | |
| import torch.nn as nn | |
| class CameraEmbedder(nn.Module): | |
| """ | |
| Embed camera features to a high-dimensional vector. | |
| Reference: | |
| DiT: https://github.com/facebookresearch/DiT/blob/main/models.py#L27 | |
| """ | |
| def __init__(self, raw_dim: int, embed_dim: int): | |
| super().__init__() | |
| self.mlp = nn.Sequential( | |
| nn.Linear(raw_dim, embed_dim), | |
| nn.SiLU(), | |
| nn.Linear(embed_dim, embed_dim), | |
| ) | |
| def forward(self, x): | |
| return self.mlp(x) | |