代码之家 › 专栏 › 技术社区 › A J

为什么我的动态神经网络有0个参数?

neural-network pytorch deep-learning

0

A J · 技术社区 · 1 年前

我定义了以下神经网络:

class Q_function(nn.Module):

    def __init__(self, input_size=3, hidden_size=5, num_layers=3, learning_rate=0.01):
        super(Q_function, self).__init__()
        self.input_size = input_size
        self.layers = []
        for i in num_layers:
            self.layers.append(nn.Linear(input_size, hidden_size)) 
            self.append(nn.ReLU())
        self.layers.append(nn.Linear(hidden_size,1))
    
    def forward(self, x):
        out = self.layers[0](x)
        for lay in range(1,len(self.layers)):
            out = self.layers[lay](out)
        return out

当我跑步时:

net = Q_function()
list(net.parameters())

我得到的输出是一个空列表 [] 。有人能解释一下为什么网络没有参数吗?如何注册参数?如何解决此问题?

1 回复 | 直到 1 年前

1

0

Karl 1 年前

Pytorch通过特定的构造函数类跟踪参数。它无法查看任意列表。

要跟踪模块列表,需要将其包装在 nn.Sequential 或 nn.ModuleList

class Q_function(nn.Module):

    def __init__(self, input_size=3, hidden_size=5, num_layers=3, learning_rate=0.01):
        super(Q_function, self).__init__()
        self.input_size = input_size
        self.layers = []
        for i in num_layers:
            self.layers.append(nn.Linear(input_size, hidden_size)) 
            self.append(nn.ReLU())
        self.layers.append(nn.Linear(hidden_size,1))
        self.layers = nn.ModuleList(self.layers)
    
    def forward(self, x):
        out = self.layers[0](x)
        for lay in range(1,len(self.layers)):
            out = self.layers[lay](out)
        return out

也就是说,在您的模型代码中也存在许多错误。你可能想要这样的东西:

class Q_function(nn.Module):

    def __init__(self, input_size=3, hidden_size=5, num_layers=3, learning_rate=0.01):
        super(Q_function, self).__init__()
        self.input_size = input_size
        self.layers = [nn.Linear(input_size, hidden_size), nn.ReLU()]
        for i in range(num_layers-1):
            self.layers.append(nn.Linear(hidden_size, hidden_size)) 
            self.layers.append(nn.ReLU())
        self.layers.append(nn.Linear(hidden_size,1))
        self.layers = nn.Sequential(*self.layers)
    
    def forward(self, x):
        x = self.layers(x)
        return x