TensorFlow – 如何创建一个热张量

TensorFlow 是由 Google 设计的开源Python库，用于开发机器学习模型和深度学习神经网络。

一个热张量是一个张量，其中 i =j 和 i!=j 的索引处的所有值都相同。

Method Used:

• one_hot: This method accepts a Tensor of indices, a scalar defining depth of the one hot dimension and returns a one hot Tensor with default on value 1 and off value 0. These on and off values can be modified.

示例 1：

Python3

# importing the library
import tensorflow as tf
  
# Initializing the Input
indices = tf.constant([1, 2, 3])
  
# Printing the Input
print("Indices: ", indices)
  
# Generating one hot Tensor
res = tf.one_hot(indices, depth = 3)
  
# Printing the resulting Tensors
print("Res: ", res )

输出：

Indices:  tf.Tensor([1 2 3], shape=(3, ), dtype=int32)
Res:  tf.Tensor(
[[0. 1. 0.]
 [0. 0. 1.]
 [0. 0. 0.]], shape=(3, 3), dtype=float32)

示例 2：此示例明确定义了一个热张量的 on 和 off 值。

Python3

# importing the library
import tensorflow as tf
  
# Initializing the Input
indices = tf.constant([1, 2, 3])
  
# Printing the Input
print("Indices: ", indices)
  
# Generating one hot Tensor
res = tf.one_hot(indices, depth = 3, on_value = 3, off_value =-1)
  
# Printing the resulting Tensors
print("Res: ", res )

输出：

Indices:  tf.Tensor([1 2 3], shape=(3, ), dtype=int32)
Res:  tf.Tensor(
[[-1  3 -1]
 [-1 -1  3]
 [-1 -1 -1]], shape=(3, 3), dtype=int32)