Spaces:
Sleeping
Sleeping
Download src/core/network/layers/linear.py from ceccurr/EquiFusion: direct link, hf CLI and curl.
- Browser
- Download file 1.24 kB
-
https://huggingface.co/spaces/ceccurr/EquiFusion/resolve/main/src/core/network/layers/linear.py
- Command line
-
hf download hf://spaces/ceccurr/EquiFusion/src/core/network/layers/linear.py
-
curl -L -o linear.py https://huggingface.co/spaces/ceccurr/EquiFusion/resolve/main/src/core/network/layers/linear.py
1.24 kB
| from typing import Tuple, Optional, List, Union | |
| import torch | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| import math | |
| class MaskedLinear2(nn.Module): | |
| def __init__(self, in_features, out_features, activation=None, bias=False): | |
| super().__init__() | |
| self.activation = activation | |
| self.weight = torch.nn.Parameter(torch.ones(out_features, in_features)) | |
| self.bias = bias | |
| nn.init.kaiming_uniform_(self.weight, a=math.sqrt(5)) | |
| if self.bias: | |
| self.bias_w = torch.nn.Parameter(torch.zeros(out_features)) | |
| fan_in, _ = nn.init._calculate_fan_in_and_fan_out(self.weight) | |
| bound = 1 / math.sqrt(fan_in) if fan_in > 0 else 0 | |
| nn.init.uniform_(self.bias_w, -bound, bound) | |
| def forward(self, input, adj: torch.Tensor = None, mask: torch.Tensor = None): | |
| # `input` is of shape (batch_size, n, n) | |
| # `mask` is of shape (batch_size, n,n) as the weigths | |
| w = self.weight | |
| input = input@w.mT | |
| if self.bias: | |
| if mask is None: | |
| mask = (adj.sum(-1) != 0).unsqueeze(-1) | |
| input = (input + self.bias_w)* mask | |
| return input if self.activation is None else self.activation(input) | |