添加中文注释

example.py

@@ -3,49 +3,63 @@ from transformer import SimpleTransformer, create_padding_mask, create_look_ahea
 
 
 def main():
-    vocab_size = 1000
-    d_model = 512
-    num_heads = 8
-    num_layers = 6
-    d_ff = 2048
-    max_seq_len = 100
+    """主函数：演示Transformer模型的使用"""
     
+    # 模型超参数配置
+    vocab_size = 1000   # 词汇表大小
+    d_model = 512       # 模型维度（嵌入维度）
+    num_heads = 8       # 多头注意力的头数
+    num_layers = 6      # Transformer编码器层数
+    d_ff = 2048         # 前馈网络隐藏层维度
+    max_seq_len = 100   # 最大序列长度
+    
+    # 创建Transformer模型实例
     model = SimpleTransformer(vocab_size, d_model, num_heads, num_layers, d_ff, max_seq_len)
     
-    batch_size = 2
-    seq_len = 10
+    # 创建随机输入数据（模拟token ids）
+    batch_size = 2  # 批次大小
+    seq_len = 10    # 序列长度
     x = np.random.randint(0, vocab_size, (batch_size, seq_len))
     
-    print("=== Simple Transformer Example ===")
-    print(f"Vocabulary size: {vocab_size}")
-    print(f"Model dimension: {d_model}")
-    print(f"Number of heads: {num_heads}")
-    print(f"Number of layers: {num_layers}")
-    print(f"Feed-forward dimension: {d_ff}")
-    print(f"Max sequence length: {max_seq_len}")
+    # 打印模型配置信息
+    print("=== 简单Transformer示例 ===")
+    print(f"词汇表大小: {vocab_size}")
+    print(f"模型维度: {d_model}")
+    print(f"注意力头数: {num_heads}")
+    print(f"编码器层数: {num_layers}")
+    print(f"前馈网络维度: {d_ff}")
+    print(f"最大序列长度: {max_seq_len}")
     print()
     
-    print(f"Input shape: {x.shape}")
-    print(f"Input sample: {x[0]}")
+    # 打印输入信息
+    print(f"输入形状: {x.shape}")
+    print(f"输入样本: {x[0]}")
     print()
     
+    # 执行前向传播
     output = model.forward(x)
     
-    print(f"Output shape: {output.shape}")
-    print(f"Output sample (first 5 values): {output[0, 0, :5]}")
+    # 打印输出信息
+    print(f"输出形状: {output.shape}")
+    print(f"输出样本（前5个值）: {output[0, 0, :5]}")
     print()
     
+    # 打印模型参数统计
     total_params = model.count_parameters()
-    print(f"Total parameters: {total_params:,}")
+    print(f"总参数量: {total_params:,}")
     print()
     
-    print("=== Attention Mask Examples ===")
-    padding_mask = create_padding_mask(x)
-    print(f"Padding mask shape: {padding_mask.shape}")
+    # 演示掩码创建
+    print("=== 注意力掩码示例 ===")
     
+    # 填充掩码（用于忽略padding位置）
+    padding_mask = create_padding_mask(x)
+    print(f"填充掩码形状: {padding_mask.shape}")
+    
+    # 前瞻掩码（用于解码器，防止看到未来信息）
     look_ahead_mask = create_look_ahead_mask(seq_len)
-    print(f"Look-ahead mask shape: {look_ahead_mask.shape}")
-    print(f"Look-ahead mask sample:\n{look_ahead_mask[:5, :5]}")
+    print(f"前瞻掩码形状: {look_ahead_mask.shape}")
+    print(f"前瞻掩码示例:\n{look_ahead_mask[:5, :5]}")
 
 
 if __name__ == "__main__":