Spaces:
Running
Running
| # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved | |
| """ | |
| Various positional encodings for the transformer. | |
| """ | |
| import math | |
| import torch | |
| from torch import nn | |
| from typing import List | |
| from typing import Optional | |
| from torch import Tensor | |
| class NestedTensor(object): | |
| def __init__(self, tensors, mask: Optional[Tensor]): | |
| self.tensors = tensors | |
| self.mask = mask | |
| def to(self, device): | |
| # type: (Device) -> NestedTensor # noqa | |
| cast_tensor = self.tensors.to(device) | |
| mask = self.mask | |
| if mask is not None: | |
| assert mask is not None | |
| cast_mask = mask.to(device) | |
| else: | |
| cast_mask = None | |
| return NestedTensor(cast_tensor, cast_mask) | |
| def decompose(self): | |
| return self.tensors, self.mask | |
| def __repr__(self): | |
| return str(self.tensors) | |
| class PositionEmbeddingSine(nn.Module): | |
| """ | |
| This is a more standard version of the position embedding, very similar to the one | |
| used by the Attention is all you need paper, generalized to work on images. | |
| """ | |
| def __init__(self, num_pos_feats=64, temperature=10000, normalize=False, scale=None): | |
| super().__init__() | |
| self.num_pos_feats = num_pos_feats | |
| self.temperature = temperature | |
| self.normalize = normalize | |
| if scale is not None and normalize is False: | |
| raise ValueError("normalize should be True if scale is passed") | |
| if scale is None: | |
| scale = 2 * math.pi | |
| self.scale = scale | |
| def forward(self, mask): | |
| assert mask is not None | |
| y_embed = mask.cumsum(1, dtype=torch.float32) | |
| x_embed = mask.cumsum(2, dtype=torch.float32) | |
| if self.normalize: | |
| eps = 1e-6 | |
| y_embed = y_embed / (y_embed[:, -1:, :] + eps) * self.scale | |
| x_embed = x_embed / (x_embed[:, :, -1:] + eps) * self.scale | |
| dim_t = torch.arange(self.num_pos_feats, dtype=torch.float32)#.cuda() | |
| dim_t = self.temperature ** (2 * (dim_t // 2) / self.num_pos_feats) | |
| pos_x = x_embed[:, :, :, None] / dim_t | |
| pos_y = y_embed[:, :, :, None] / dim_t | |
| pos_x = torch.stack((pos_x[:, :, :, 0::2].sin(), pos_x[:, :, :, 1::2].cos()), dim=4).flatten(3) | |
| pos_y = torch.stack((pos_y[:, :, :, 0::2].sin(), pos_y[:, :, :, 1::2].cos()), dim=4).flatten(3) | |
| pos = torch.cat((pos_y, pos_x), dim=3).permute(0, 3, 1, 2) | |
| # print(pos.shape) | |
| return pos | |
| class PositionEmbeddingLearned(nn.Module): | |
| """ | |
| Absolute pos embedding, learned. | |
| """ | |
| def __init__(self, num_pos_feats=256): | |
| super().__init__() | |
| self.row_embed = nn.Embedding(50, num_pos_feats) | |
| self.col_embed = nn.Embedding(50, num_pos_feats) | |
| self.reset_parameters() | |
| def reset_parameters(self): | |
| nn.init.uniform_(self.row_embed.weight) | |
| nn.init.uniform_(self.col_embed.weight) | |
| def forward(self, tensor_list: NestedTensor): | |
| x = tensor_list.tensors | |
| h, w = x.shape[-2:] | |
| i = torch.arange(w, device=x.device) | |
| j = torch.arange(h, device=x.device) | |
| x_emb = self.col_embed(i) | |
| y_emb = self.row_embed(j) | |
| pos = torch.cat([ | |
| x_emb.unsqueeze(0).repeat(h, 1, 1), | |
| y_emb.unsqueeze(1).repeat(1, w, 1), | |
| ], dim=-1).permute(2, 0, 1).unsqueeze(0).repeat(x.shape[0], 1, 1, 1) | |
| return pos | |
| def build_position_encoding(hidden_dim=512, position_embedding='sine'): | |
| N_steps = hidden_dim // 2 | |
| if position_embedding in ('v2', 'sine'): | |
| position_embedding = PositionEmbeddingSine(N_steps, normalize=True) | |
| elif position_embedding in ('v3', 'learned'): | |
| position_embedding = PositionEmbeddingLearned(N_steps) | |
| else: | |
| raise ValueError(f"not supported {position_embedding}") | |
| return position_embedding | |