unet.py

""" Parts of the U-Net model """

import torch
import torch.nn as nn
import torch.nn.functional as F
from transformers import Wav2Vec2Model


class UNet(nn.Module):
    def __init__(self, 
        input_dim, # ssl_dim + stft_dim = 768 + 201 = 969
        n_classes, # stft_dim = 201
        input_channels, 
        bilinear=True, 
    ):
        super(UNet, self).__init__()
        self.input_dim = input_dim
        self.n_classes = n_classes
        self.input_channels = input_channels
        self.bilinear = bilinear
        self.type = type

        factor = 2 if bilinear else 1

        self.inc = (DoubleConv(self.input_channels, 64))
        self.down1 = (DownSamplingLayer(64, 128))
        self.down2 = (DownSamplingLayer(128, 256))
        self.down3 = (DownSamplingLayer(256, 512))
        self.down4 = (DownSamplingLayer(512, 1024 // factor))
        self.up1 = (UpSamplingLayer(1024, 512 // factor, bilinear))
        self.up2 = (UpSamplingLayer(512, 256 // factor, bilinear))
        self.up3 = (UpSamplingLayer(256, 128 // factor, bilinear))
        self.up4 = (UpSamplingLayer(128, 64, bilinear))
        self.outc = (OutConv(64, self.n_classes))
        self.dim_stft = 201 # TODO: change without hardcoding
        self.linear_projection = torch.nn.Linear(self.input_dim, self.dim_stft)

    def forward(self, x):
        x1 = self.inc(x)
        x2 = self.down1(x1)
        x3 = self.down2(x2)
        x4 = self.down3(x3)
        x5 = self.down4(x4)
        x = self.up1(x5, x4)
        x = self.up2(x, x3)
        x = self.up3(x, x2)
        x = self.up4(x, x1)
        logits = self.outc(x)
        logits = self.linear_projection(logits)
        return logits

class DoubleConv(nn.Module):
    """(convolution => [BN] => ReLU) * 2"""

    def __init__(self, in_channels, out_channels, mid_channels=None):
        super().__init__()
        if not mid_channels:
            mid_channels = out_channels
        self.double_conv = nn.Sequential(
            nn.Conv2d(in_channels, mid_channels, kernel_size=3, padding=1, bias=False),
            nn.BatchNorm2d(mid_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(mid_channels, out_channels, kernel_size=3, padding=1, bias=False),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True)
        )

    def forward(self, x):
        return self.double_conv(x)


class DownSamplingLayer(nn.Module):
    """Downscaling with maxpool then double conv"""

    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.maxpool_conv = nn.Sequential(
            nn.MaxPool2d(2),
            DoubleConv(in_channels, out_channels)
        )

    def forward(self, x):
        return self.maxpool_conv(x)

class UpSamplingLayer(nn.Module):
    """Upscaling then double conv"""

    def __init__(self, in_channels, out_channels, bilinear=True):
        super().__init__()

        # if bilinear, use the normal convolutions to reduce the number of channels
        if bilinear:
            self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
            self.conv = DoubleConv(in_channels, out_channels, in_channels // 2)
        else:
            self.up = nn.ConvTranspose2d(in_channels, in_channels // 2, kernel_size=2, stride=2)
            self.conv = DoubleConv(in_channels, out_channels)

    def forward(self, x1, x2):
        x1 = self.up(x1)
        # input is CHW
        diffY = x2.size()[2] - x1.size()[2]
        diffX = x2.size()[3] - x1.size()[3]
        x1 = F.pad(x1, [diffX // 2, diffX - diffX // 2,
                        diffY // 2, diffY - diffY // 2])
        x = torch.cat([x2, x1], dim=1)
        return self.conv(x)


class OutConv(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(OutConv, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1)

    def forward(self, x):
        return self.conv(x)