Method forward

segmentation/backbones/cgnet.py:335–362

(self, x)

            nn.PReLU(cur_channels))

    def forward(self, x):
        output = []

        # stage 0
        inp_2x = self.inject_2x(x)
        inp_4x = self.inject_4x(x)
        for layer in self.stem:
            x = layer(x)
        x = self.norm_prelu_0(torch.cat([x, inp_2x], 1))
        output.append(x)

        # stage 1
        for i, layer in enumerate(self.level1):
            x = layer(x)
            if i == 0:
                down1 = x
        x = self.norm_prelu_1(torch.cat([x, down1, inp_4x], 1))
        output.append(x)

        # stage 2
        for i, layer in enumerate(self.level2):
            x = layer(x)
            if i == 0:
                down2 = x
        x = self.norm_prelu_2(torch.cat([down2, x], 1))
        output.append(x)

        return output

    def train(self, mode=True):
        """Convert the model into training mode will keeping the normalization