Python Pytorch randn()用法及代码示例

PyTorch Torch.randn()返回由可变参数大小(定义输出张量的形状的整数序列)定义的张量，其中包含标准正态分布的随机数。

用法：torch.randn(*size, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False)

让我们借助几个示例来了解这个概念：

范例1：

# import pytorch library 
import torch 
  
# create a tensor of size 2 x 4 
input_var = torch.randn(2,4) 
  
print (input_var)

输出：

tensor([[-1.4313, -0.3831, -0.8356, -1.5555],
        [-1.2749, -1.1872, -0.4983,  0.1029]])

这将返回一个大小为2×4的张量，其中填充了标准正态分布的值，即均值为0而方差为1。

范例2：

# import Pytorch library 
import torch 
  
# create a 3-dimensionl tensor 
# of 4 x 5 
input_var =  torch.randn(3, 4, 5,  
                     requires_grad = True) 
print(input_var)

输出：

tensor([[[-0.1097,  1.6845,  0.9375, -1.0515,  0.5767],
        [ 0.1924, -0.7736, -0.7102, -0.2654,  0.3118],
        [-0.5314,  0.1924, -1.1629,  0.2360,  0.8605],
        [-0.8036, -0.0695, -0.6062,  1.4872,  0.5455]],

       [[ 1.5699, -0.7190,  1.0925,  0.8463, -0.1906],
        [-0.0763, -0.6819, -1.0517, -0.5087, -1.4451],
        [-2.0127,  1.0061,  0.5723, -0.1336, -0.3821],
        [ 0.0868,  1.1556,  0.3842, -0.4168, -1.4604]],

       [[ 0.1368, -1.6240, -0.1875, -0.5964,  0.9352],
        [ 0.4429,  0.2843, -1.2151,  1.3456, -0.4539],
        [-0.4528,  1.9981, -1.2007,  0.0071, -0.0239],
        [-0.1003,  0.7938, -0.0977, -1.4097,  0.1679]]], requires_grad=True)  

返回一个张量为3×4×5的张量，其中填充有随机数，并且在执行时还记录了梯度值。
范例3：

# import Pytorch library 
import torch 
  
# error occur 
input_var =  torch.randn(3.0, 4.0, 5.0, 
                     requires_grad = True) 
print(input_var)

输出：

TypeError                                 Traceback (most recent call last)
in
     1 # import Pytorch library
     2 import torch
—-> 3 input =  torch.randn(3.0, 4.0, 5.0,requires_grad=True)
     4 print( input )

TypeError:randn() received an invalid combination of arguments - got (float, float, float, requires_grad=bool), but expected one of:
* (tuple of ints size, *, tuple of names names, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
* (tuple of ints size, *, torch.Generator generator, tuple of names names, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
* (tuple of ints size, *, torch.Generator generator, Tensor out, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
* (tuple of ints size, *, Tensor out, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)

size参数不能采用浮点数，因此会产生错误。