import torch
import torch.nn as nn
import torch.nn.utils as utils

def discriminator_block(in_channels, out_channels, kernel_size=3, stride=1, dilation=1, spectral_norm=True):
    padding = (kernel_size // 2) * dilation
    conv_layer = nn.Conv1d(in_channels, out_channels, kernel_size=kernel_size, stride=stride, dilation=dilation, padding=padding)
    if spectral_norm:
        conv_layer = utils.spectral_norm(conv_layer)
    return nn.Sequential(
        conv_layer,
        nn.LeakyReLU(0.2, inplace=True),
        nn.BatchNorm1d(out_channels)
    )

class AttentionBlock(nn.Module):
    def __init__(self, channels):
        super(AttentionBlock, self).__init__()
        self.attention = nn.Sequential(
            nn.Conv1d(channels, channels // 4, kernel_size=1),
            nn.ReLU(),
            nn.Conv1d(channels // 4, channels, kernel_size=1),
            nn.Sigmoid()
        )

    def forward(self, x):
        attention_weights = self.attention(x)
        return x * attention_weights

class SISUDiscriminator(nn.Module):
    def __init__(self, layers=4): #Increased base layer count
        super(SISUDiscriminator, self).__init__()
        self.model = nn.Sequential(
            discriminator_block(1, layers, kernel_size=7, stride=4), #Aggressive downsampling
            discriminator_block(layers, layers * 2, kernel_size=5, stride=2),
            discriminator_block(layers * 2, layers * 4, kernel_size=5, dilation=2),
            discriminator_block(layers * 4, layers * 8, kernel_size=5, dilation=4),
            AttentionBlock(layers * 8), #Added attention
            discriminator_block(layers * 8, layers * 16, kernel_size=5, dilation=8),
            discriminator_block(layers * 16, layers * 16, kernel_size=3, dilation=1),
            discriminator_block(layers * 16, layers * 8, kernel_size=3, dilation=2),
            discriminator_block(layers * 8, layers * 4, kernel_size=3, dilation=1),
            discriminator_block(layers * 4, layers * 2, kernel_size=3, stride=1),
            discriminator_block(layers * 2, layers, kernel_size=3, stride=1),
            discriminator_block(layers, 1, kernel_size=3, stride=1, spectral_norm=False) #last layer no spectral norm.
        )
        self.global_avg_pool = nn.AdaptiveAvgPool1d(1)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        x = self.model(x)
        x = self.global_avg_pool(x)
        x = x.view(-1, 1)
        x = self.sigmoid(x)
        return x