import torch
import torch.nn as nn

N_VEL = 2
N_SUB = 2
state_dim = N_VEL * N_SUB
num_actions = 2 ** (N_SUB * N_VEL)
M = 16


class Net(nn.Module):
    def __init__(self, n_input_channels, n_actions):
        ## input channels 是数据的输入的维度
        ## 每个状态是一个
        ## N * N * (M_c + 1)的tensor
        ## 其中 N * N 代表的是用户的数量 如果有1000个用户 大概为32
        ## 第M_c个matrix代表的是当前用户的申请或是离开
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=n_input_channels, out_channels=16, kernel_size=5, stride=1, padding=0)
        self.conv2 = nn.Conv2d(in_channels=16, out_channels=32, kernel_size=3, stride=1, padding=0)
        self.fc1 = nn.Linear(in_features=4 * 4 * 32, out_features=512)
        self.fc2 = nn.Linear(in_features=512, out_features=512)
        self.fc3 = nn.Linear(in_features=512, out_features=n_actions)
        # nn.init.normal_(self.fc1.weight, 0., 0.1)
        # nn.init.constant_(self.fc1.bias, 0.1)
        # self.fc2 = nn.Linear(500, 300)
        # nn.init.normal_(self.fc2.weight, 0., 0.1)
        # nn.init.constant_(self.fc2.bias, 0.1)
        # self.fc3 = nn.Linear(300, 250)
        # nn.init.normal_(self.fc3.weight, 0., 0.1)
        # nn.init.constant_(self.fc3.bias, 0.1)
        # self.fc4 = nn.Linear(250, n_actions)
        # nn.init.normal_(self.fc4.weight, 0., 0.1)
        # nn.init.constant_(self.fc4.bias, 0.1)

    def forward(self, x):
        x = torch.sigmoid(self.conv1(x))
        x = torch.sigmoid(self.conv2(x))
        x = x.view(x.size(0), -1)
        x = torch.sigmoid(self.fc1(x))
        x = torch.sigmoid(self.fc2(x))
        output = self.fc3(x)
        return output


if __name__ == "__main__":
    input_channels = 10 * 10 * 16
    num_actions = 16
    q_network = Net(input_channels, num_actions)

    print(q_network)