torch.compile (inductor)

import torch
import torch.nn as nn

# U-Net Implementation
class DoubleConv(nn.Module):
    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.double_conv = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1),
            nn.BatchNorm2d(out_channels),
            nn.Softmax(dim=-1),
            nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1),
            nn.BatchNorm2d(out_channels),
            nn.Softmax(dim=-1)
        )

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

class Model(nn.Module):
    def __init__(self, in_channels, out_channels, features):
        """
        :param in_channels: Number of input channels
        :param out_channels: Number of output channels
        :param features: Number of base features (will be doubled in each layer)
        """
        super(Model, self).__init__()
        self.encoder1 = DoubleConv(in_channels, features)
        self.pool1 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.encoder2 = DoubleConv(features, features * 2)
        self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.encoder3 = DoubleConv(features * 2, features * 4)
        self.pool3 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.encoder4 = DoubleConv(features * 4, features * 8)
        self.pool4 = nn.MaxPool2d(kernel_size=2, stride=2)

        self.bottleneck = DoubleConv(features * 8, features * 16)

        self.upconv4 = nn.ConvTranspose2d(features * 16, features * 8, kernel_size=2, stride=2)
        self.decoder4 = DoubleConv(features * 16, features * 8)
        self.upconv3 = nn.ConvTranspose2d(features * 8, features * 4, kernel_size=2, stride=2)
        self.decoder3 = DoubleConv(features * 8, features * 4)
        self.upconv2 = nn.ConvTranspose2d(features * 4, features * 2, kernel_size=2, stride=2)
        self.decoder2 = DoubleConv(features * 4, features * 2)
        self.upconv1 = nn.ConvTranspose2d(features * 2, features, kernel_size=2, stride=2)
        self.decoder1 = DoubleConv(features * 2, features)

        self.final_conv = nn.Conv2d(features, out_channels, kernel_size=1)

    def forward(self, x):
        """
        :param x: Input tensor, shape (batch_size, in_channels, height, width)
        :return: Output tensor, shape (batch_size, out_channels, height, width)
        """
        enc1 = self.encoder1(x)
        enc2 = self.encoder2(self.pool1(enc1))
        enc3 = self.encoder3(self.pool2(enc2))
        enc4 = self.encoder4(self.pool3(enc3))

        bottleneck = self.bottleneck(self.pool4(enc4))

        dec4 = self.upconv4(bottleneck)
        dec4 = torch.cat((dec4, enc4), dim=1)
        dec4 = self.decoder4(dec4)
        dec3 = self.upconv3(dec4)
        dec3 = torch.cat((dec3, enc3), dim=1)
        dec3 = self.decoder3(dec3)
        dec2 = self.upconv2(dec3)
        dec2 = torch.cat((dec2, enc2), dim=1)
        dec2 = self.decoder2(dec2)
        dec1 = self.upconv1(dec2)
        dec1 = torch.cat((dec1, enc1), dim=1)
        dec1 = self.decoder1(dec1)

        return self.final_conv(dec1)
    
batch_size = 8
in_channels = 8
out_channels = 4
height = 64
width = 512
features = 64
# Test code for UNet
def get_inputs():
    return [torch.rand(batch_size, in_channels, height, width)]

def get_init_inputs():
    return [in_channels, out_channels, features]