Python Pytorch empty()用法及代碼示例

PyTorch是由Facebook開發的開源機器學習庫。它用於深度神經網絡和自然語言處理。

函數torch.empty()返回填充有未初始化數據的張量。張量的形狀由可變的參數大小定義。

用法:torch.empty(size, out=None)

代碼1：

# Importing the PyTorch library 
import torch 
  
  
# Applying the empty function and 
# storing the resulting tensor in 'a' 
a = torch.empty([3, 4]) 
print("a = ", a) 
  
b = torch.empty([2, 3]) 
print("b = ", b)

輸出：

a =  tensor([[2.0283e-19, 6.9772e+22, 1.8943e+23, 1.1432e-32],
        [1.3563e-19, 1.8888e+31, 8.9066e-15, 1.8888e+31],
        [6.4639e-04, 6.8608e+22, 1.7753e+28, 2.0535e-19]])
b =  tensor([[0., 0., 0.],
        [0., 0., 0.]])