[人工智能]shape && size

一、shape && size

shape和size是在numpy中使用的属性/方法

• shape：返回矩阵的形状
• size：返回矩阵内元素的个数

shape和size在tensor中也可以使用，均返回矩阵的形状

import torch
import numpy as np

tensor = torch.tensor([[1, 2, 3], [4, 5, 6]])
array = np.array([[1, 2, 3], [4, 5, 6]])

# size和shape作为tensor的方法和属性
print("tensor.size():       ", tensor.size())
print("tensor.shape:        ", tensor.shape)

# size和shape作为array的属性
print("array.size:          ", array.size)
print("array.shape:         ", array.shape)

# size和shape作为array的方法
print("np.size(array):      ", np.size(array))
print("np.size(array, 0):   ", np.size(array, 0))
print("np.size(array, 1):   ", np.size(array, 1))
print("np.shape(array):     ", np.shape(array))
# torch_data = torch.from_numpy(np_data)
# tensor2array = torch_data.numpy()

二、numpy && tensor互转

1. numpy—>tensor

tensor = torch.from_numpy(array)

2. tensor—>numpy

array = tensor.numpy()