目录

一、Tensr

1、Tensor属性

2、创建

(1)  

Creation Ops

 (2) 其它

二、Tensor基本操作

Indexing, Slicing, Joining, Mutating Ops

三、Random sampling

四、数学运算

1、按元素操作 

（1）加减乘除、绝对值

（2）指数、对数、幂运算、开方运算

（3）三角&反三角函数运算函数运算

（4）双曲线反双曲线运算

  (5) 其他常用操作

（6） 

BLAS and LAPACK Operations

---

一、Tensr

1、Tensor属性

numel  # Returns the total number of elements in the input tensor.
repeat_interleaves
 
 
>>> a = torch.randn(1, 2, 3, 4, 5)
>>> torch.numel(a)
120
>>> a = torch.zeros(4,4)
>>> torch.numel(a)
16
 
 
>>> x = torch.tensor([1, 2, 3])
>>> x.repeat_interleave(2)
tensor([1, 1, 2, 2, 3, 3])
>>> y = torch.tensor([[1, 2], [3, 4]])
>>> torch.repeat_interleave(y, 2)
tensor([1, 1, 2, 2, 3, 3, 4, 4])
>>> torch.repeat_interleave(y, 3, dim=1)
tensor([[1, 1, 1, 2, 2, 2],
        [3, 3, 3, 4, 4, 4]])
>>> torch.repeat_interleave(y, torch.tensor([1, 2]), dim=0)
tensor([[1, 2],
        [3, 4],
        [3, 4]])
>>> torch.repeat_interleave(y, torch.tensor([1, 2]), dim=0, output_size=3)
tensor([[1, 2],
        [3, 4],
        [3, 4]]

2、创建

前言 · PyTorch实用教程（第二版）

(1)  

• Creation Ops

 (2) 其它

>>> torch.eye(3)
tensor([[ 1.,  0.,  0.],
        [ 0.,  1.,  0.],
        [ 0.,  0.,  1.]])

二、Tensor基本操作

Indexing, Slicing, Joining, Mutating Ops

tensor.stack()
tensor.cat()
torch.squeeze()
torch.unsqueeze()
 
 
>>> x = torch.zeros(2, 1, 2, 1, 2)
>>> x.size()
torch.Size([2, 1, 2, 1, 2])
>>> y = torch.squeeze(x)
>>> y.size()
torch.Size([2, 2, 2])
>>> y = torch.squeeze(x, 0)
>>> y.size()
torch.Size([2, 1, 2, 1, 2])
>>> y = torch.squeeze(x, 1)
>>> y.size()
torch.Size([2, 2, 1, 2])

三、Random sampling

bernoulli
multinomial
normal
poisson
 
rand
rand_like
randint
randint_like
randn
randn_like
randperm
 
 
# In-place random sampling
torch.Tensor.bernoulli_() 
torch.Tensor.cauchy_()
 
torch.Tensor.exponential_() 
torch.Tensor.geometric_() 
torch.Tensor.log_normal_() 
 
torch.Tensor.normal_()
torch.Tensor.random_() 
torch.Tensor.uniform_() 

四、数学运算

1、按元素操作 

torch — PyTorch 1.12 documentationhttps://pytorch.org/docs/stable/torch.html#pointwise-ops

（1）加减乘除、绝对值

add 
sub # subtract, Alias for torch.sub().
mul # multiply, Alias for torch.mul().
div # divide , Alias for torch.div().
 
abs # absolute, Alias for torch.abs()

加法举例：

import torch
a_list = [[1, -2, 3], [-4, 5, -6]]
a_tensor = torch.tensor(list1)
print(a_tensor)
 
# output:
tensor([[ 1, -2,  3],
        [-4,  5, -6]])
 
 
# 加法操作
# ops 1
a_tensor.add(10)
# output1
tensor([[11,  8, 13],
        [ 6, 15,  4]])
 
# ops 2
b_tensor = torch.ones_like(a_tensor)
a_tensor.add(b_tensor, alpha=19) # alpha=1(默认)，a_tensor = alpha*b_tensor + a_tensor
 
# output1
tensor([[20, 17, 22],
        [15, 24, 13]])

（2）指数、对数、幂运算、开方运算

（3）三角&反三角函数运算函数运算

（4）双曲线反双曲线运算

  (5) 其他常用操作

clamp  
reshape
view

clamp  # clip Alias for torch.clamp().
 
a = torch.randn(4)
# output1
tensor([-1.7120,  0.1734, -0.0478, -0.0922])
 
 
torch.clamp(a, min=-0.5, max=0.5)
# output2
tensor([-0.5000,  0.1734, -0.0478, -0.0922])

（6） 

• BLAS and LAPACK Operations

# torch.bmm
>>> input = torch.randn(10, 3, 4)
>>> mat2 = torch.randn(10, 4, 5)
>>> res = torch.bmm(input, mat2)
>>> res.size()
torch.Size([10, 3, 5])

参考：   torch.clamp — PyTorch 1.12 documentation 

PyTorch：view() 与 reshape() 区别详解_地球被支点撬走啦的博客-CSDN博客_reshape和view

torch.repeat_interleave — PyTorch 1.12 documentation