# Codeblock 7a
class ZF5_SPPNet(nn.Module):
    def __init__(self):
        super().__init__()
        
        self.relu = nn.ReLU()
        
        
        self.conv1 = nn.Conv2d(in_channels=3, 
                               out_channels=96, 
                               kernel_size=7, 
                               stride=2, 
                               padding=0)    #(1)
        self.norm1 = nn.LocalResponseNorm(size=5)
        self.pool1 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)    #(2)
        
        
        self.conv2 = nn.Conv2d(in_channels=96, 
                               out_channels=256, 
                               kernel_size=5, 
                               stride=2, 
                               padding=1)    #(3)
        self.norm2 = nn.LocalResponseNorm(size=5)
        self.pool2 = nn.MaxPool2d(kernel_size=3, stride=2, padding=0)    #(4)
        
        
        self.conv3 = nn.Conv2d(in_channels=256, 
                               out_channels=384, 
                               kernel_size=3, 
                               stride=1, 
                               padding=1)
        
        self.conv4 = nn.Conv2d(in_channels=384, 
                               out_channels=384, 
                               kernel_size=3, 
                               stride=1, 
                               padding=1)
        
        self.conv5 = nn.Conv2d(in_channels=384, 
                               out_channels=256, 
                               kernel_size=3, 
                               stride=1, 
                               padding=1)
        
        self.spp = SPP()    #(4)
        spp_out_size = 256 * sum([grid**2 for grid in GRIDS])    #(5)
        
        self.fc6 = nn.Linear(in_features=spp_out_size, out_features=4096)
        self.dropout6 = nn.Dropout(p=0.5)    #(6)
        
        self.fc7 = nn.Linear(in_features=4096, out_features=4096)
        self.dropout7 = nn.Dropout(p=0.5)    #(7)
        
        self.fc8 = nn.Linear(in_features=4096, out_features=1000)