68多头注意力

import math
import torch
from torch import nn
from d2l import torch as d2l

# 选择缩放点积注意力作为每一个注意力头
# 

标签：hiddens,heads,self,batch,多头,num,68,注意力,size	

From： https://www.cnblogs.com/g932150283/p/16597086.html