如何在 PyTorch 中对张量执行逐元素乘法？

在本文中，我们将了解如何在Python中的 PyTorch 中对张量执行逐元素乘法。我们可以使用 torch.mul() 方法执行元素相加。

这个函数还允许我们对相同或不同维度的张量进行乘法运算。如果张量的维度不同，那么它将返回更高维度的张量。我们还可以使用 torch.mul()函数将标量与张量相乘。

Syntax: torch.mul(input, other, *, out=None)

Parameters:

• input: This is input tensor.
• other: The value or tensor that is to be multiply to every element of tensor.
• out: it is the output tensor, This is optional parameter.

Return: returns a new modified tensor..

示例 1：

下面的程序是对两个单维张量进行乘法运算。

Python3

# import torch library
import torch
 
# define two tensors
tens_1 = torch.Tensor([1, 2, 3, 4, 5])
tens_2 = torch.Tensor([10, 20, 30, 40, 50])
 
# display tensors
print(" First Tensor: ", tens_1)
print(" Second Tensor: ", tens_2)
 
# multiply tensors
tens = torch.mul(tens_1, tens_2)
 
# display result after perform element wise multiplication
print(" After Element-wise multiplication: ", tens)

输出：

 First Tensor:  tensor([1., 2., 3., 4., 5.])

 Second Tensor:  tensor([10., 20., 30., 40., 50.])

 After Element-wise multiplication:  tensor([ 10.,  40.,  90., 160., 250.])

示例 2：

下面的程序是要知道如何将一个标量乘以一个张量。

Python3

# import torch library
import torch
 
# define a tensors
tens_1 = torch.Tensor([100, 200, 300, 400, 500])
 
# display tensor
print(" First Tensor: ", tens_1)
 
# multiply a scalar tensors
tens = torch.mul(tens_1, 2)
 
# display result after perform element wise multiplication
print(" After multiply 2 in tensor: ", tens)

输出：

 First Tensor:  tensor([100., 200., 300., 400., 500.])

 After multiply 2 in tensor:  tensor([ 200.,  400.,  600.,  800., 1000.])

示例 3：

下面的程序是在二维张量上执行元素乘法。

Python3

# import torch
import torch
 
# Define two 2D tensors
tens_1 = torch.Tensor([[10, 20], [30, 40]])
tens_2 = torch.Tensor([[1, 2], [3, 4]])
 
# display tensors
print(" First tensor:  ", tens_1)
print(" Second tensor:  ", tens_2)
 
# Multiply above two 2-D tensors
tens = torch.mul(tens_1, tens_2)
print(" After multiply 2D tensors: ", tens)

输出：

First tensor:   tensor([[10., 20.],[30., 40.]])
 Second tensor:   tensor([[1., 2.],[3., 4.]])
 After multiply 2D tensors:  tensor([[ 10.,  40.],[ 90., 160.]])

示例 4：

以下程序将展示如何在两个不同维度的张量上执行逐元素乘法。

Python3

# import torch
import torch
 
# Define two 2D tensors
tens_1 = torch.Tensor([[10, 20], [30, 40]])
tens_2 = torch.Tensor([2, 4])
 
# display tensors
print(" 2D tensor: ", tens_1)
print(" 1D tensor:  ", tens_2)
 
# Multiply above two 2-D tensors
tens = torch.mul(tens_1, tens_2)
print(" After multiply tensors: ", tens)

输出：

2D tensor:  tensor([[10., 20.],
        [30., 40.]])
 1D tensor:   tensor([2., 4.])
 After multiply tensors:  tensor([[ 20.,  80.],
        [ 60., 160.]])