a4697d7e45e66a3264eb56dcf489d67d4df40d23,implementations/cgan/cgan.py,Discriminator,__init__,#Discriminator#,74

Before Change

                block.append(nn.BatchNorm2d(out_filters, 0.8))
            return block

        layers = []
        in_filters = opt.channels + 1
        for out_filters, bn in [(16, False), (32, True), (64, True), (128, False)]:
            layers.extend(discriminator_block(in_filters, out_filters, bn))
            in_filters = out_filters

After Change

        self.label_embedding = nn.Embedding(opt.n_classes, opt.n_classes)

        self.model = nn.Sequential(
            nn.Linear(opt.n_classes + opt.img_size**2, 512),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Linear(512, 512),
            nn.Dropout(0.4),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Linear(512, 512),
            nn.Dropout(0.4),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Linear(512, 1),
            nn.Sigmoid()
        )

    def forward(self, img, labels):
        // Concatenate label embedding and image by channels
        d_input = torch.cat((img.view(img.size(0), -1), self.label_embedding(labels)), -1)

Instances