# Codeblock 8
class Darknet53(nn.Module):
    def __init__(self):
        super().__init__()

        self.convolutional0 = Convolutional(in_channels=3,
                                            out_channels=32,
                                            kernel_size=3)
        
        self.convolutional1 = Convolutional(in_channels=32,
                                            out_channels=64,
                                            kernel_size=3,
                                            stride=2)
        
        self.residuals0 = nn.ModuleList([Residual(num_channels=64) for _ in range(1)])
        
        self.convolutional2 = Convolutional(in_channels=64,
                                            out_channels=128,
                                            kernel_size=3,
                                            stride=2)
        
        self.residuals1 = nn.ModuleList([Residual(num_channels=128) for _ in range(2)])
        
        self.convolutional3 = Convolutional(in_channels=128,
                                            out_channels=256,
                                            kernel_size=3,
                                            stride=2)
        
        self.residuals2 = nn.ModuleList([Residual(num_channels=256) for _ in range(8)])
        
        self.convolutional4 = Convolutional(in_channels=256,
                                            out_channels=512,
                                            kernel_size=3,
                                            stride=2)
        
        self.residuals3 = nn.ModuleList([Residual(num_channels=512) for _ in range(8)])
        
        self.convolutional5 = Convolutional(in_channels=512,
                                            out_channels=1024,
                                            kernel_size=3,
                                            stride=2)
        
        self.residuals4 = nn.ModuleList([Residual(num_channels=1024) for _ in range(4)])
        
    def forward(self, x):
        print(f'original\t\t: {x.size()}\n')
        
        x = self.convolutional0(x)
        print(f'after convolutional0\t: {x.size()}')
        
        x = self.convolutional1(x)
        print(f'after convolutional1\t: {x.size()}\n')
        
        for i in range(len(self.residuals0)):
            x = self.residuals0[i](x)
            print(f'after residuals0 #{i}\t: {x.size()}')
        
        x = self.convolutional2(x)
        print(f'\nafter convolutional2\t: {x.size()}\n')
        
        for i in range(len(self.residuals1)):
            x = self.residuals1[i](x)
            print(f'after residuals1 #{i}\t: {x.size()}')
            
        x = self.convolutional3(x)
        print(f'\nafter convolutional3\t: {x.size()}\n')
        
        for i in range(len(self.residuals2)):
            x = self.residuals2[i](x)
            print(f'after residuals2 #{i}\t: {x.size()}')
        
        branch0 = x.clone()           #(1)
            
        x = self.convolutional4(x)
        print(f'\nafter convolutional4\t: {x.size()}\n')
        
        for i in range(len(self.residuals3)):
            x = self.residuals3[i](x)
            print(f'after residuals3 #{i}\t: {x.size()}')
        
        branch1 = x.clone()           #(2)
            
        x = self.convolutional5(x)
        print(f'\nafter convolutional5\t: {x.size()}\n')
        
        for i in range(len(self.residuals4)):
            x = self.residuals4[i](x)
            print(f'after residuals4 #{i}\t: {x.size()}')
            
        return branch0, branch1, x    #(3)