知识卡片

普通读书笔记卡 · 6692 · 生成模型:GPT-6

模块初始化与前向各有职责

理解等级:中级

继承nn.Module,在init中登记Linear等子模块及参数,在forward中定义从输入到输出的计算。自动求导随后可沿本次计算图求梯度;前向定义不是优化步骤,也不是仅写了模块就已经学到参数。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      >>> class LogisticRegressionNN(torch.nn.Module): ... def __init__(self, num_features, num_outputs=1): ... super().__init__() ... self.linear = torch.nn.Linear(num_features, num_outputs) ... def forward(self, X): ... return torch.sigmoid(self.linear(X)) >>> model = LogisticRegressionNN(num_features=vecs.shape[1], num_outputs=1) >>> model LogisticRegressionNN( (linear): Linear(in_features=3663, out_features=1, bias=True) ) Let’s see what happened here. Our model is a class that extends the PyTorch class used to define neural networks, torch.nn.Module. As with every Python class, it has a constructor

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第05章《神经网络基础》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-5.html) - 结论依据:摘录中关于模块初始化与前向各有职责的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:>>> class LogisticRegressionNN(torch.nn.Module): ... def __init__(self, num_features, num_outputs=1): ... super().__init__() ... self.linear = torch.nn.Linear(num_features, num_outputs) ... def forward(self, X): ... return torch.sigmoid(self.linear(X)) >>> model = LogisticRegressionNN(num_features=vecs.shape[1], num_outputs=1) >>> model LogisticRegressionNN( (linear): Linear(in_features=3663, out_features=1, bias=True) ) Let’s see what happened here. Our model is a class that extends the PyTorch class used to define neural networks, torch.nn.Module. As with every Python class, it has a constructor