align/models.py [385:401]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        layers = list()
        hidden_dims = [input_dim] + hidden_dims
        for i in range(1, len(hidden_dims)):
            layers.append(nn.Linear(hidden_dims[i-1], hidden_dims[i]))
            layers.append(nn.ReLU())
        layers.append(nn.Linear(hidden_dims[-1], output_dim))
        layers.append(nn.Sigmoid())
        self.model = nn.Sequential(*layers)
        self.bias = nn.Parameter(torch.ones(feature_transform))
        self.feature_transform = feature_transform

    def forward(self, x):
        transformed_features = torch.cat([x[:, :-self.feature_transform], torch.log(x[:, -self.feature_transform:] + self.bias.abs())], dim=-1)
        return self.model(transformed_features)

    def __call__(self, *args, **kwargs):
        return self.forward(*args, **kwargs)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/models.py [60:76]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        layers = list()
        hidden_dims = [input_dim] + hidden_dims
        for i in range(1, len(hidden_dims)):
            layers.append(nn.Linear(hidden_dims[i-1], hidden_dims[i]))
            layers.append(nn.ReLU())
        layers.append(nn.Linear(hidden_dims[-1], output_dim))
        layers.append(nn.Sigmoid())
        self.model = nn.Sequential(*layers)
        self.bias = nn.Parameter(torch.ones(feature_transform))
        self.feature_transform = feature_transform

    def forward(self, x):
        transformed_features = torch.cat([x[:, :-self.feature_transform], torch.log(x[:, -self.feature_transform:] + self.bias.abs())], dim=-1)
        return self.model(transformed_features)

    def __call__(self, *args, **kwargs):
        return self.forward(*args, **kwargs)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -