custom.py 文件源码

def forward(self, inputs):
        current_input = inputs

        for i in range(0, len(self.layers), 2):
            layer, activation = self.layers[i], self.layers[i+1]
            proj, linear = layer(current_input), current_input
            proj = F.dropout(proj, p=self.dropout, training=self.training)
            nonlinear = activation(proj[:, 0:self.input_dim])
            gate = F.sigmoid(proj[:, self.input_dim:(2 * self.input_dim)])

            # apply gate
            current_input = gate * linear + (1 - gate) * nonlinear

        return current_input

# gracefully taken from:
# https://discuss.pytorch.org/t/solved-reverse-gradients-in-backward-pass/3589/4