Spaces:
Paused
Paused
| # ------------------------------------------------------------------------ | |
| # Copyright (c) 2022 IDEA. All Rights Reserved. | |
| # Licensed under the Apache License, Version 2.0 [see LICENSE for details] | |
| # ------------------------------------------------------------------------ | |
| # Modified from Mask2Former https://github.com/facebookresearch/Mask2Former by Feng Li and Hao Zhang. | |
| """ | |
| Various positional encodings for the transformer. | |
| """ | |
| import math | |
| import torch | |
| from torch import nn | |
| 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, x, mask=None): | |
| if mask is None: | |
| mask = torch.zeros((x.size(0), x.size(2), x.size(3)), device=x.device, dtype=torch.bool) | |
| not_mask = ~mask | |
| y_embed = not_mask.cumsum(1, dtype=torch.float32) | |
| x_embed = not_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, device=x.device) | |
| 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) | |
| return pos | |
| def __repr__(self, _repr_indent=4): | |
| head = "Positional encoding " + self.__class__.__name__ | |
| body = [ | |
| "num_pos_feats: {}".format(self.num_pos_feats), | |
| "temperature: {}".format(self.temperature), | |
| "normalize: {}".format(self.normalize), | |
| "scale: {}".format(self.scale), | |
| ] | |
| # _repr_indent = 4 | |
| lines = [head] + [" " * _repr_indent + line for line in body] | |
| return "\n".join(lines) | |