3. 编写程序，创建一个tensor，要求： ① 四维、32位浮点型、

大小为(2,3,4,5)；②随机初始化。

答案：

import torch

tensor = torch.randn(2, 3, 4, 5, dtype=torch.float32)

print(tensor)

相关问题

3. 编写程序，创建一个tensor，要求： 四维、32位浮点型

可以使用Python中的NumPy库来创建一个四维、32位浮点型的tensor，代码如下：

import numpy as np

tensor = np.zeros((1, 2, 3, 4), dtype=np.float32)

这个代码创建了一个四维的tensor，其形状为(1, 2, 3, 4)，即第一维有1个元素，第二维有2个元素，第三维有3个元素，第四维有4个元素。其中，dtype参数指定了数据类型为32位浮点型。

编写程序，创建一个tensor，要求： ①四维、32位浮点型、名字是自己姓名全拼； 数字自己定，至少有24个数，但是不能有相同的数字，也不能按顺序赋值。

import tensorflow as tf

# 姓名全拼：zhangsan
tensor = tf.constant([
[
[
[3.1415, 2.718, 0.618, 0.123],
[1.618, 0.666, 0.999, 0.777],
[0.111, 0.222, 0.333, 0.444],
[0.555, 0.777, 0.888, 0.999]
],
[
[1.234, 5.678, 9.101, 1.111],
[0.222, 0.333, 0.444, 0.555],
[1.111, 2.222, 3.333, 4.444],
[5.555, 6.666, 7.777, 8.888]
],
[
[9.999, 8.888, 7.777, 6.666],
[5.555, 4.444, 3.333, 2.222],
[1.111, 0.222, 0.333, 0.444],
[0.555, 0.777, 0.888, 0.999]
],
[
[1.111, 2.222, 3.333, 4.444],
[5.555, 6.666, 7.777, 8.888],
[9.999, 8.888, 7.777, 6.666],
[5.555, 4.444, 3.333, 2.222]
]
],
[
[
[0.111, 0.222, 0.333, 0.444],
[0.555, 0.777, 0.888, 0.999],
[3.1415, 2.718, 0.618, 0.123],
[1.618, 0.666, 0.999, 0.777]
],
[
[1.234, 5.678, 9.101, 1.111],
[0.222, 0.333, 0.444, 0.555],
[1.111, 2.222, 3.333, 4.444],
[5.555, 6.666, 7.777, 8.888]
],
[
[9.999, 8.888, 7.777, 6.666],
[5.555, 4.444, 3.333, 2.222],
[1.111, 0.222, 0.333, 0.444],
[0.555, 0.777, 0.888, 0.999]
],
[
[5.555, 6.666, 7.777, 8.888],
[9.999, 8.888, 7.777, 6.666],
[5.555, 4.444, 3.333, 2.222],
[1.111, 2.222, 3.333, 4.444]
]
]
], dtype=tf.float32, name="zhangsan")

print(tensor)