Python – tensorflow.convert_to_tensor()

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。

convert_to_tensor()用于将给定值转换为张量

Syntax: tensorflow.convert_to_tensor( value, dtype, dtype_hint, name )

Parameters:

• value: It is the value that needed to be converted to Tensor.
• dtype(optional): It defines the type of the output Tensor.
• dtype_hint(optional): It is used when dtype is None. In some cases, a caller may not have a dtype in mind when converting to a tensor, so dtype_hint can be used as a soft preference. If the conversion to dtype_hint is not possible, this argument has no effect.
• name(optiona): It defines the name for the operation.

Returns: It returns a Tensor.

示例 1：来自Python列表

Python3

# Importing the library
import tensorflow as tf
  
# Initializing the input
l = [1, 2, 3, 4]
  
# Printing the input
print('l: ', l)
  
# Calculating result
x = tf.convert_to_tensor(l)
  
  
# Printing the result
print('x: ', x)

输出：

l:  [1, 2, 3, 4]
x:  tf.Tensor([1 2 3 4], shape=(4, ), dtype=int32)

示例 2：来自Python元组

Python3

# Importing the library
import tensorflow as tf
  
# Initializing the input
l = (1, 2, 3, 4)
  
# Printing the input
print('l: ', l)
  
# Calculating result
x = tf.convert_to_tensor(l, dtype = tf.float64)
  
  
# Printing the result
print('x: ', x)

输出：

l:  (1, 2, 3, 4)
x:  tf.Tensor([1. 2. 3. 4.], shape=(4, ), dtype=float64)