model.py

import torch
import torch.nn as nn

device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

class ConvNet(nn.Module):
    def __init__(self, name, num_classes=10):
        super(ConvNet, self).__init__()
        self.name = name
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.fc = nn.Linear(7*7*32, num_classes)

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out

model_full = ConvNet(name='original').to(device)
model_to_quantify = ConvNet(name='quantized').to(device)

class AutoQuantizedNet(nn.Module):
    def __init__(self, name, num_classes=10):
        super(AutoQuantizedNet, self).__init__()
        self.name = name
        self.relu = nn.ReLU()
        self.maxpool = nn.MaxPool2d(kernel_size=2, stride=2)
        self.conv1 = nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2)
        self.bn1 = nn.BatchNorm2d(16)
        self.conv2 = nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2)
        self.bn2 = nn.BatchNorm2d(32)
        self.fc = nn.Linear(7*7*32, num_classes)

    def forward(self, x):
        out = self.relu(self.bn1(self.conv1(x)))
        out = self.maxpool(out)
        out = self.relu(self.bn2(self.conv2(out)))
        out = self.maxpool(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out

model_auto = AutoQuantizedNet(name='autoquantize').to(device)