torch.compile (inductor)

import torch
import torch.nn as nn

class Model(nn.Module):
    """
    Model that performs a 3D convolution, max pooling, log sum exp, and ReLU activation.
    """
    def __init__(self, in_channels, out_channels, kernel_size, stride, padding):
        super(Model, self).__init__()
        self.conv = nn.Conv3d(in_channels, out_channels, kernel_size, stride=stride, padding=padding)
        self.max_pool = nn.MaxPool3d(kernel_size=2, stride=2)

    def forward(self, x):
        """
        Args:
            x: Input tensor of shape (batch_size, in_channels, depth, height, width)
        Returns:
            Output tensor of shape (batch_size, out_channels, depth', height', width')
        """
        x = self.conv(x)
        x = self.max_pool(x)
        x = torch.logsumexp(x, dim=1, keepdim=True)
        x = torch.relu(x)
        return x

batch_size = 4
in_channels = 32
out_channels = 64
depth, height, width = 32, 128, 128
kernel_size = 3
stride = 1
padding = 1

def get_inputs():
    return [torch.rand(batch_size, in_channels, depth, height, width)]

def get_init_inputs():
    return [in_channels, out_channels, kernel_size, stride, padding]