PyTorch中的张量数学运算

1. 加减乘除
   torch.add(input, alpha=1, other, out=None)
   torch.addcdiv(tensor, value=1, tensor1, tensor2, out=None)
   torch.addcmul(tensor, value=1, tensor1, tensor2, out=None)
   torch.sub(input, other, out=None)
   torch.mul(input, other, out=None)
   torch.div(input, other, out=None)

2. 对数，指数，幂函数
   torch.log(input, out=None) ——以e为底
   torch.log10(input, out=None)
   torch.log2(input, out=None)
   torch.exp(input, out=None)
   torch.pow(input, exponent, out=None)

3. 三角函数
   torch.acos(input, out=None)
   torch.cosh(input, out=None)
   torch.cos(input, out=None)
   torch.asin(input, out=None)
   torch.sinh(input, out=None)
   torch.sin(input, out=None)
   torch.atan(input, out=None)
   torch.tanh(input, out=None)
   torch.tan(input, out=None)
   torch.atan2(input, other, out=None)

4. 绝对值
   torch.abs(input, out=None)

torch.add()

torch.add(input, 
          alpha=1, 
          other, 
          out=None)

功能： 逐元素计算 input+alpha×other，因为深度学习中经常用到先乘后加的操作，所以增加了此功能，可以使代码更加整洁

• input: 第一个张量
• alpha: 乘项因子
• other: 第二个张量

torch.addcdiv()

torch.addcdiv(tensor, 
              value=1, 
              tensor1, 
              tensor2, 
              out=None) 

功能： 逐元素计算 $out=input+value\times \frac{tensor1}{tensor2}$，优化过程中常用

torch.addcmul()

torch.addcmul(tensor, 
              value=1, 
              tensor1, 
              tensor2, 
              out=None) 

功能： 逐元素计算 $out=input+value\times tensor1\times tensor2$，优化过程中常用

torch.atan2()

torch.atan2(input, 
            other, 
            out=None)

功能： Element-wise arctangent of $\frac{inpu{t}_i}{othe{r}_i}$ with consideration of the quadrant. Returns a new tensor with the signed angles in radians between vector ($othe{r}_i,inpu{t}_i$) and vector (1, 0).
注意： $othe{r}_i$, the second parameter, is the x-coordinate, while $inpu{t}_i$, the first parameter, is the y-coordinate.