标准化归一化 batch norm, layer norm, group norm, instance norm

Layer Normalization - EXPLAINED (in Transformer Neural Networks)

Layer Normalization - EXPLAINED (in Transformer Neural Networks)

0~4min:什么是multi-head attention

请添加图片描述

5~7min:layer norm图示

请添加图片描述

7~9min:公式举例layer norm

请添加图片描述

9:54-end:layer norm的代码示例

group norm

猜你喜欢

转载自blog.csdn.net/duoyasong5907/article/details/132115895