PyTorch torch.normal Function
Pytorch torch Reference Manual
torch.normalis a function in PyTorch used to generate random numbers from a normal distribution.
Function Definition
torch.normal(mean, std, *, generator=None, out=None) torch.normal(mean, std, size, *, generator=None, out=None)
Parameter Description
mean- Mean of the normal distributionstd- Standard deviation of the normal distributionsize- Shape of the output tensor (optional)generator- Random number generator (optional)out- Output tensor (optional)
Usage Example
Example
import torch
# Generate a random tensor using fixed mean and standard deviation
result1 = torch.normal(mean=0.0, std=1.0, size=(3, 3))
print("Mean 0, standard deviation 1 3x3 normal distribution random tensor:")
print(result1)
# Use tensors as mean and standard deviation
mean = torch.tensor([0.0, 1.0, 2.0])
std = torch.tensor([1.0, 2.0, 3.0])
result2 = torch.normal(mean, std)
print("nSampling result using tensor parameters:")
print(result2)
# Use scalar mean and tensor standard deviation
result3 = torch.normal(mean=0.0, std=torch.tensor([1.0, 2.0, 3.0]))
print("nSampling result with scalar mean and tensor standard deviation:")
print(result3)
# Generate a random tensor using fixed mean and standard deviation
result1 = torch.normal(mean=0.0, std=1.0, size=(3, 3))
print("Mean 0, standard deviation 1 3x3 normal distribution random tensor:")
print(result1)
# Use tensors as mean and standard deviation
mean = torch.tensor([0.0, 1.0, 2.0])
std = torch.tensor([1.0, 2.0, 3.0])
result2 = torch.normal(mean, std)
print("nSampling result using tensor parameters:")
print(result2)
# Use scalar mean and tensor standard deviation
result3 = torch.normal(mean=0.0, std=torch.tensor([1.0, 2.0, 3.0]))
print("nSampling result with scalar mean and tensor standard deviation:")
print(result3)
Other Extensions