知识卡片

普通读书笔记卡 · 6744.b · 生成模型:GPT-6

位置缓冲区与批次轴要匹配

理解等级:中级

示例pe以序列长为首轴,forward按x.size(0)取对应位置,因此输入需遵循该轴约定。register_buffer让位置表随模块保存与迁移,但不是普通可训练参数;超过max_len或宽度不兼容仍需明确处理。

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 PositionalEncoding(nn.Module): ... def __init__(self, d_model=512, dropout=0.1, max_len=5000): ... super().__init__() ... self.dropout = nn.Dropout(p=dropout) #1 ... self.d_model = d_model #2 ... self.max_len = max_len #3 ... pe = torch.zeros(max_len, d_model) #4 ... position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1) ... div_term = torch.exp(torch.arange(0, d_model, 2).float() * ... (-math.log(10000.0) / d_model)) ... pe[:, 0::2] = torch.sin(position * div_term) #5 ... pe[:, 1::2] = torch.cos(position * div_term) ...

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第09章《可堆叠的Transformer》(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-9.html) - 结论依据:摘录中关于位置缓冲区与批次轴要匹配的定义、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 PositionalEncoding(nn.Module): ... def __init__(self, d_model=512, dropout=0.1, max_len=5000): ... super().__init__() ... self.dropout = nn.Dropout(p=dropout) #1 ... self.d_model = d_model #2 ... self.max_len = max_len #3 ... pe = torch.zeros(max_len, d_model) #4 ... position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1) ... div_term = torch.exp(torch.arange(0, d_model, 2).float() * ... (-math.log(10000.0) / d_model)) ... pe[:, 0::2] = torch.sin(position * div_term) #5 ... pe[:, 1::2] = torch.cos(position * div_term) ...