class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()

        self.act_max = nn.Parameter(torch.Tensor([0]), requires_grad=True)

        self.conv1 = nn.Conv2d(3, 32, kernel_size=5)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=5)
        self.pool = nn.MaxPool2d(2, 2)
        self.relu = nn.ReLU()
        self.linear = nn.Linear(64 * 5 * 5, 10)

    def forward(self, input):
        conv1 = self.conv1(input)
        pool1 = self.pool(conv1)
        relu1 = self.relu(pool1)

        relu1[relu1 > self.act_max] = self.act_max

        conv2 = self.conv2(relu1)
        pool2 = self.pool(conv2)
        relu2 = self.relu(pool2)
        relu2 = relu2.view(relu2.size(0), -1)
        linear = self.linear(relu2)
        return linear


model = Net()
torch.nn.init.kaiming_normal_(model.parameters)
nn.init.constant(model.act_max, 1.0)
model = model.cuda()
optimizer = torch.optim.SGD(model.parameters(), lr=0.001)
for epoch in range(100):
    for i in range(1000):
        output = model(input)
        loss = nn.CrossEntropyLoss()(output, label)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        model.act_max.data = model.act_max.data - 0.001 * model.act_max.grad.data