import torch
from torch import nn
import torch.nn.functional as F


malware_classes = ['7ev3n', 'APosT', 'Adposhel', 'Agent', 'Agentb', 'Allaple', 'Alueron.gen!J', 'Amonetize', 
                   'Androm', 'Bashlite', 'Bingoml', 'Blacksoul', 'BrowseFox', 'C2LOP.gen!g', 'Convagent', 'Copak', 
                   'Delf', 'Dialplatform.B', 'Dinwod', 'Elex', 'Emotet', 'Escelar', 'Expiro', 'Fakerean', 'Fareit', 
                   'Fasong', 'GandCrab', 'GlobelImposter', 'GootLoader', 'HLLP', 'HackKMS', 'Hlux', 'IcedId', 'Infy', 
                   'Inject', 'Injector', 'InstallCore', 'KRBanker', 'Koadic', 'Kryptik', 'Kwampirs', 'Lamer', 
                   'LemonDuck', 'Loki', 'Lolyda.AA1', 'Lolyda.AA2', 'Mimail', 'MultiPlug', 'Mydoom', 'Neoreklami', 
                   'Neshta', 'NetWireRAT', 'Ngrbot', 'OnlinerSpambot', 'Orcus', 'Padodor', 'Plite', 'PolyRansom', 
                   'QakBot', 'QtBot', 'Qukart', 'REvil', 'Ramdo', 'Regrun', 'Rekt Loader', 'Sakula', 'Salgorea', 
                   'Scar', 'SelfDel', 'Small', 'Snarasite', 'Stantinko', 'Trickpak', 'Upantix', 'Upatre', 'VB', 
                   'VBA', 'VBKrypt', 'VBNA', 'Vilsel', 'Vobfus', 'WBNA', 'Wecod', 'XTunnel', 'Zenpak', 'Zeus', 'benign']

class DenseLayer(nn.Module):
    def __init__(self, in_channels, growth_rate, bn_size):
        super(DenseLayer, self).__init__()
        self.bn1 = nn.BatchNorm2d(in_channels)
        self.conv1 = nn.Conv2d(in_channels, bn_size * growth_rate, kernel_size=1, bias=False)
        self.bn2 = nn.BatchNorm2d(bn_size * growth_rate)
        self.conv2 = nn.Conv2d(bn_size * growth_rate, growth_rate, kernel_size=3, padding=1, bias=False)
        
    def forward(self, x):
        out = self.conv1(F.relu(self.bn1(x)))
        out = self.conv2(F.relu(self.bn2(out)))
        return torch.cat([x, out], 1)

class DenseBlock(nn.Module):
    def __init__(self, num_layers, in_channels, growth_rate, bn_size):
        super(DenseBlock, self).__init__()
        layers = []
        for i in range(num_layers):
            layers.append(DenseLayer(in_channels + i * growth_rate, growth_rate, bn_size))
        self.layers = nn.Sequential(*layers)
    
    def forward(self, x):
        return self.layers(x)

class TransitionLayer(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(TransitionLayer, self).__init__()
        self.bn = nn.BatchNorm2d(in_channels)
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1, bias=False)
        self.pool = nn.AvgPool2d(kernel_size=2, stride=2)
        
    def forward(self, x):
        out = self.conv(F.relu(self.bn(x)))
        return self.pool(out)

class MalwareNet(nn.Module):
    def __init__(self, growth_rate=32, block_config=(6, 12, 24, 16), num_init_features=64, bn_size=4, compression_rate=0.5, num_classes=87):
        super(MalwareNet, self).__init__()
        
        # First convolution
        self.features = nn.Sequential(
            nn.Conv2d(3, num_init_features, kernel_size=7, stride=2, padding=3, bias=False),
            nn.BatchNorm2d(num_init_features),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        )
        
        # Dense blocks
        num_features = num_init_features
        for i, num_layers in enumerate(block_config):
            block = DenseBlock(num_layers, num_features, growth_rate, bn_size)
            self.features.add_module(f'denseblock{i+1}', block)
            num_features += num_layers * growth_rate
            if i != len(block_config) - 1:
                transition = TransitionLayer(num_features, int(num_features * compression_rate))
                self.features.add_module(f'transition{i+1}', transition)
                num_features = int(num_features * compression_rate)
        
        # Final batch norm
        self.features.add_module('norm5', nn.BatchNorm2d(num_features))
        
        # Linear layer
        self.classifier = nn.Linear(num_features, num_classes)
        
    def forward(self, x):
        features = self.features(x)
        out = F.relu(features)
        out = F.adaptive_avg_pool2d(out, (1, 1))
        out = torch.flatten(out, 1)
        out = self.classifier(out)
        return out