class ConvNet(nn.module):
    def __init__(self, num_class=10):
        super(ConvNet, self).__init__()
        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)
        print(out.size())
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out

# Test the model
model.eval()  # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

def freeze_bn(m):
    if isinstance(m, nn.BatchNorm2d):
        m.eval()
model.apply(freeze_bn)